JP6728507B2 - Low power integrated circuit for analyzing digitized audio streams - Google Patents

Description

Computing devices are becoming more sophisticated for users by processing audio instructions and providing responses. A user may read aloud voice instructions that may be used to control these computing devices. For example, a user may speak to a computing device to provide information, such as instructions to provide a journey to a particular location.

In the accompanying drawings, the same reference numerals refer to the same components or blocks. The following detailed description refers to the drawings.

FIG. 1 illustrates an exemplary computing device including a low power integrated circuit for analyzing an audio stream and a processor for analyzing a digitized audio stream in response to detection of a keyword by the integrated circuit. It is a block diagram. FIG. 2 is a block diagram of an exemplary low power integrated circuit for analyzing a voice stream and signaling a processor to increase power if a keyword is detected in the voice stream. FIG. 3 illustrates an exemplary computing device for analyzing a digitized audio stream and a server in communication with the computing device for analyzing a text stream generated from the digitized audio stream. It is a block diagram. FIG. 4 is a flowchart of an exemplary method performed on a computing device for receiving an audio stream and determining a response. FIG. 5 is a flow chart of an exemplary method performed on a computing device to compress a digitized audio stream and present a response.

Detailed description

In voice information processing, a user typically activates an application for processing voice by pressing buttons and/or reading instructions. Launching a voice processing application requires the user to additionally read out explicit instructions that they may want the computing device to perform. Therefore, processing speech commands from the user can be time consuming and repetitive. In addition, constantly monitoring commands from the user consumes a lot of power and drains the battery.

To address these issues, the exemplary embodiments disclosed herein use a low power integrated circuit to generate the appearance of keywords in an audio stream (eg, a user's speech). , While relying on the processor for a more thorough analysis of the user's voice. For example, various examples disclosed herein receive a voice stream in a low power integrated circuit, digitize the voice stream, and analyze the digitized voice stream to recognize keywords. Provide what to do. When a keyword is recognized in the digitized audio stream, the integrated circuit signals the processor to increase power. As the power to the processor increases, the digitized audio stream is searched to determine the response. This reduces the amount of time the user spends invoking a particular voice processing application and prevents repetitive user speech. Determining a response from the retrieved audio stream prevents the user from providing additional explicit instructions to cause the computing device to perform speech analysis.

Additionally, in various examples disclosed herein, as the power to the processor increases, the processor retrieves the digitized audio stream from memory and converts the digitized audio stream to a text stream. .. After conversion to a text stream, the processor determines a response based on the text in the text stream. Determining the response from the text stream reduces the time for the computing device user to command the computing device. Additionally, the processor may also determine an appropriate response based on the context of the audio stream. In addition, the computing device determines which application needs to be executed to fulfill the response to the user. Furthermore, due to the increased power to the processor when keywords are recognized in the digitized audio stream, the computing device listens to the user while consuming less power.

In one embodiment, the computing device may also determine the response by receiving the response from the server or from the processor. In a further embodiment, the memory maintains the stored digitized audio stream for a predetermined time period. In this embodiment, the processor may search the digitized audio stream for time increments. For example, the processor may retrieve a complete digitized audio stream or a shorter time interval digitized audio stream. Retrieval of the digitized audio stream allows the processor to analyze the context of the audio stream and determine the appropriate response.

Thus, the exemplary embodiments disclosed herein prevent repetitive voice commands to the computing device because the computing device determines an appropriate response based on the context of the voice stream. This saves the user time. Further, the computing device receives and processes the audio stream while consuming less power.

Referring now to the drawings, FIG. 1 illustrates a low power integrated circuit 104 for receiving an audio stream 102 and a digitizing module for digitizing the audio stream and providing a digitized audio stream 114 in a memory 112. 1 is a block diagram of an exemplary computing device 100 including. Further, the low power integrated circuit 104 compares the digitized audio stream 114 with the keywords and, based on the recognition of the keywords, sends a signal 116 to the processor 118 to increase the power 122, the keyword comparison module 108. including. Furthermore, the processor includes an analysis module 120 for analyzing the digitized audio stream 114. Embodiments of computing device 100 include a client device, personal computer, desktop computer, laptop, mobile device, or other computing device suitable for including components 104, 112, and 118.

The audio stream 102 is received by the computing device 100, in particular the low power integrated circuit 104. Audio stream 102 is an input analog signal that is digitized 106 to provide digitized audio stream 114. Embodiments of audio stream 102 include speech from a user or audio from another computing device. For example, there may be several computing devices 100 that receive the audio stream 102, which may be confusing. Thus, a computing device may designate one device as a central point for receiving audio stream 102. In this embodiment, the low power integrated circuit 104 operates as part of an ad hoc network, which may be a central unit of one or more computing devices.

For example, a user may discuss the shortest route from New York to Los Angeles, California with another person. In this example, the audio stream would be the shortest route discussion from New York to Los Angeles. In a further embodiment, audio stream 102 may include audio over a predetermined time period. For example, audio stream 102 may include seconds or minutes when received by low power integrated circuit 104. In this example, low power integrated circuit 104 may distinguish audio stream 102 from other audio streams 102.

The low power integrated circuit 104 includes a module 106 for digitizing the audio stream 102 and a module 108 for comparing the digitized audio stream 114 with keywords. Low power integrated circuit 104 is an electronic circuit having patterned trace elements on the surface of a material that forms the interconnection between other electronic components. For example, low power integrated circuit 104 forms a connection between processor 118 and memory 112. Embodiments of low-power integrated circuit 104 can receive audio stream 102 and send signals 116, such as microchips, chipsets, electronic circuits, chips, microprocessors, semiconductors, microcontrollers, or other electronic circuits. including. The low power integrated circuit 104 can constantly monitor the audio stream 102, utilize the digitizing module 106 to digitize the audio stream, and store the digitized audio stream in the memory 112. Thus, further embodiments of low power integrated circuit 104 include a transmitter, receiver, microphone, or other suitable component for receiving audio stream 102.

The audio stream is digitized at module 106 to provide digitized audio stream 114. The digitization module 106 transforms the audio stream into a discrete time signal representation. Embodiments of digitization module 106 include analog-to-digital converters (ADCs), digital conversion devices, instructions, firmware, and/or software that operate with low power integrated circuit 104. For example, digitization module 106 may include an electronic device for converting an input analog voltage into a digital number proportional to the magnitude of the analog signal.

Once the audio stream 102 has been digitized at module 106, it is compared at module 108 to the keywords . In module 108, to the audio stream 102 increases power 122, to analyze the module 120 acquires the digitized audio stream 114, it operates as indication for signaling 116 to the processor 118, to keywords Are compared. Embodiments of 108 include instructions, processes, acts, logic, algorithms, techniques, logical functions, firmware, and/or software. When the keyword is recognized, the low power integrated circuit 104 sends a signal 116 to the processor 118 to increase the power 122.

Keyword embodiments include digital signals, analog signals, patterns, databases, commands, instructions, instructions, or other representations for comparison at module 108. For example, a user of a computing device may wish to discuss the difference between shrimp and prawns with a friend and then perform a web search to identify the answer. As such, the user may assert certain keywords to trigger recognition of the keywords by the keyword comparison module 108 and subsequent analysis of the previous discussion by the analysis module 120.

Keywords can include, for example, phrases, single keywords, or single keywords that are private to the user of the computing device. Based on the previous example, the keyword could be the phrase "What do you think a computer is?" In this example, this phrase causes low power integrated circuit 104 to send signal 116 to processor 118 to obtain digitized audio stream 114, which may include audio before or after this phrase. Thus, the processor 118 analyzes the digitized audio stream 114 to determine the context of the audio stream 102 for a proper response so that the user need not repeat the instructions. Also, in a further example, the single keyword may include "Shazam." Thus, as a particular example, when a user speaks the word “jajang”, the circuit 104 detects to the keyword and tells the processor 118 to take the digitized audio stream 114 and convert this stream into a text stream. A signal 116 may be transmitted to instruct. Assuming the text stream is a command to compose a text message to the user's mother, a suitable response would be to compose a text message. Thus, as described above, using the predetermined keyword(s), the low power integrated circuit 104 may require the user of the computing device to complete further responses such as performing a journey or a web search. recognize.

In a further embodiment of module 108, if the keyword is not recognized in digitized audio stream 114, low power integrated circuit 104 may output another audio stream 102 digitized at module 106 and stored in memory 112. Continue to monitor. In yet another embodiment, the low power integrated circuit 104 compresses the digitized audio stream 114, which is compressed by comparing the keywords with the keywords at module 108. Used to recognize.

The memory 112 stores and/or maintains the digitized audio stream 114. Embodiments of the memory 112 can store and/or maintain a digitized audio stream 114, such as memory buffers, caches, non-volatile memory, volatile memory, random access memory (RAM), electrically erasable. Programmable read only memory (EEPROM), storage drive, compact disc read only memory (CDDROM), or other memory.

The digitized audio stream 114 is stored in the memory 112. Embodiments may include low power integrated circuit 104 compressing audio stream 102 after digitizing module 106 to obtain a compressed digitized audio stream prior to placement in memory 112. Although FIG. 1 shows the digitized audio stream 114 stored in the memory 112, the digitized audio stream may also be stored in memory on the low power integrated circuit 104. In a further embodiment, digitized audio stream 114 comprises audio stream 102 of a predetermined length of time. In this embodiment, when the audio stream 102 is received for a predetermined time period, such as seconds or minutes, the audio stream 102 for the predetermined time period is digitized for acquisition and/or retrieval by the processor 118. Stored in the memory 112. Further, in this embodiment, if another audio stream 102 was received and digitized by the low power integrated circuit 104, the previous digitized audio stream in memory is closer to the present digitized audio stream 114. Is replaced by Therefore, the processor 118 retrieves and/or retrieves the most current audio stream 102. In this embodiment, the memory acts as a first-in first-out buffer to provide the most current audio stream 102.

The signal 116 is transmitted from the low power integrated circuit 104 to the processor 118 upon the recognition of the keyword in the digitized audio stream 114. The signal 116 increases the power 122 and directs the processor 118 to analyze the digitized audio stream 114 from the memory 112. Embodiments of signal 116 include communications, transmissions, electrical signals, instructions, digital signals, analog signals, or other types of communications to processor 118 to increase power 122. A further embodiment of signal 116 includes an interrupt sent to processor 118 when a keyword is recognized in digitized audio stream 114.

Processor 118 receives signal 116 to increase power 122 and obtain digitized audio stream 114 for analysis by module 120. Embodiments of the processor 118 may include a central processing unit (CPU), visual processing unit (VPU), microprocessor, graphics processing unit (GPU), or other suitable for analyzing 120 the digitized audio stream 114. It may include a programmable device.

Once the processor 118 obtains the digitized audio stream 114 from the memory 112, the processor analyzes the digitized audio stream 114 at module 120. Embodiments of analysis module 120 include instructions, processes, operations, logic, algorithms, techniques, logical functions, firmware, and/or software that processor 118 may fetch, decode, and/or execute. Additional embodiments of module 120 include converting the digitized audio stream 114 to a text stream and determining an appropriate response based on the context of audio stream 102. Further embodiments of module 120 include determining a response to present to a user of computing device 100, as seen in later figures.

Electric power 122 supplies electrical energy to processor 118 in the form of a potential. In particular, the power 122 increases electrical energy to the processor 118 when the signal 116 is received from the low power integrated circuit 104. Increasing power 122 to processor 118 wakes or triggers processor 118 to acquire digitized audio stream 114. Embodiments of power 122 include power supplies, power management devices, batteries, energy storage, electromechanical systems, solar power, power plugs, or other devices that can provide power 122 to processor 118. In a further embodiment, power 122 provides electrical energy to computing device 100.

Referring now to FIG. 2, an exemplary low power integrated circuit 204 for analyzing the audio stream 202 and sending a signal 216 to the processor to increase power if a keyword is detected in the audio stream 202. It is a block diagram of. Low power integrated circuit 204 includes circuitry 210 for generating digitized audio stream 214 using digitizing circuitry 206, detecting keywords by comparison circuitry 208 and digitizing audio stream. Upon recognizing the keyword during 214, it sends signal 216.

Audio stream 202 is received by low power integrated circuit 204. The audio stream 202 may be similar in structure to the audio stream 102 of FIG.

The low power integrated circuit 204 includes circuitry 210 for digitizing the audio stream 202 and comparing the digitized audio stream 214 with keywords. The low power integrated circuit 204 may be similar in function and structure to the low power integrated circuit 104 described above in FIG.

The circuit element 210 includes a digitizing circuit element 206 and a comparing circuit element 208. Embodiments of the circuit element 210 can digitize the audio stream 202 and compare the digitized audio stream 214 with keywords, such as logic, analog circuit elements, electronic circuit elements, digital circuit elements, or other circuit elements. including. In a further embodiment, the circuit elements may include applications and/or firmware that may be utilized independently and/or together with the low power integrated circuit 204 to fetch, decode, and / or execute the circuit elements 206 and 208. Including.

The audio stream 202 is received by the circuit element 206 and digitized to produce a digitized audio stream 214. Digitization circuitry 206 is the type of transformation for audio stream 202. Further, the digitizing circuitry 206 may be similar in function to the digitizing module 106 described in connection with FIG.

The low power integrated circuit 204 receives the audio stream 202 and digitizes it in circuit elements 206 to produce a digitized audio stream 214. The digitized audio stream 214 may be similar in structure to the digitized audio stream 114 described in connection with FIG. Further, although FIG. 2 shows the digitized audio stream 214 outside the low power integrated circuit 204, the digitized audio stream 214 may also be located within the low power integrated circuit 204. The digitized audio stream 214 located in the low power integrated circuit 204 is used by the circuit element 208 for comparison with keywords. In another embodiment, the digitized audio stream 214 is stored and/or maintained in memory.

The circuit element 208 included in the circuit element 210 of the low power integrated circuit 204 compares the digitized audio stream 214 with the keywords. In addition, 208 is used to recognize the keywords in the digitized audio stream 214 and send a signal 216 to the processor to increase power. The comparator circuit element 208 may be similar in function to the module 108 described in connection with FIG.

Signal 216 directs the device to increase power when a keyword is recognized in digitized audio stream 214 by comparison circuitry 208. Signal 216 may be similar in structure and function to signal 116 of FIG. Embodiments of signal 216 include instructing a processor to increase power and analyze digitized audio stream 214 from memory. In this embodiment, signal 216 directs the processor to acquire and analyze digitized audio stream 214 and determine a response based on keyword recognition at circuit element 208.

FIG. 3 communicates with an exemplary computing device 300 for analyzing a digitized audio stream 314 and a computing device 300 for analyzing a text stream 324 generated from the digitized audio stream 314. 3 is a block diagram of a server 326 that executes Computing device 300 includes low power integrated circuit 304, memory 312, processor 318, output device 328, and server 326. In particular, FIG. 3 illustrates a text stream 324 that is processed by a server 326 or processor 318 to present a response at a output device 324 to a user of a computing device. Computing device 300 may be similar in structure and function to computing device 100 described in connection with FIG.

The audio stream 302 is received by the computing device 300, particularly low power integrated circuit 304. The audio stream 302 may be similar in structure to the respective audio streams 102 and 202 in FIGS. 1 and 2.

The low power integrated circuit 304 includes a digitization module 306 and an analysis module 308. In one embodiment, low power integrated circuit 304 includes circuit elements to comprise modules 306 and 308. The low power integrated circuit 304 may be similar in structure and function to the low power integrated circuits 104 and 204 described in connection with FIGS. 1 and 2, respectively.

Upon receipt by the computing device 300, the audio stream 302 is digitized 306 to produce a digitized audio stream 314. Digitization module 306 may be similar in structure and function to digitization module 106 and digitization circuitry 206, respectively in FIGS. 1 and 2. In a further embodiment, once the audio stream 302 is digitized at the module 306, the low power integrated circuit 304 sends the digitized audio stream 314 to the memory 312 for storage and/or maintenance.

Once the audio stream 314 is digitized, the low power integrated circuit analyzes the digitized audio stream 314 at module 308. In one embodiment, the module 308 compares the keyword with the digitized audio stream 314 . In this embodiment, 308 includes the functionality of the comparison module 108 described above in FIG.

The memory 312 stores the digitized audio stream 314 from the low power integrated circuit 304. In one embodiment, the memory 312 maintains the digitized audio stream 314 received during the predetermined time period. For example, the audio stream 302 can be monitored for a predetermined time of a few seconds, and thus the few seconds of the audio stream 302 is digitized at module 306 and sent to memory 312. In this example, memory 312 stores a few seconds of digitized audio stream 314 so that upon receipt of signal 316, it may be retrieved and/or retrieved by processor 318 for analysis. Also, in this example, if a few seconds of another audio stream 302 is received and digitized, this other digitized audio stream 314 replaces the previous digitized audio stream 314. This allows the memory 312 to maintain the latest audio stream 302 for acquisition and/or retrieval by the processor 318. The memory 312 may be similar in structure and function to the memory 112 described in connection with FIG.

The audio stream 302 is digitized 306 to produce a digitized audio stream 314. The digitized audio stream 314 is stored and/or maintained in memory 312. In an embodiment, the processor 318, upon receiving the signal 316, obtains the digitized audio stream 314 and analyzes it at the module 320. Digitized audio stream 314 may be similar in structure and function to digitized audio streams 114 and 214 described in connection with FIGS. 1 and 2, respectively.

Signal 316 is a transmission from low power integrated circuit 304 to processor 318 to increase power 322. Embodiments of signal 316 additionally direct processor 318 to obtain digitized audio stream 314 for analysis at module 320. Signal 316 may be similar in structure and function to signals 116 and 216 described in connection with FIGS. 1 and 2, respectively.

Electric power 322 provides electrical energy to processor 318 and/or computing device 300. The power 322 may be similar in structure and function to the power 122 described in connection with FIG.

Processor 318 includes analysis module 320 and text stream 324. In particular, processor 318 receives signal 316 to increase power 322. Upon receipt of this signal 316, the processor 318 obtains the digitized audio stream 314 for analysis by the module 320. In a further embodiment, the processor 318 converts the digitized audio stream 314 into a text stream 324. In this embodiment, the text in text stream 324 commands a response for computing device 300. A text stream is a string of a finite sequence of symbols or expressions from an alphabet, a set of numbers, or a set of alphanumeric characters. For example, the digitized audio stream 314 may be in a binary language, so the processor translates the binary representation bytes into words. In a further example, digitized audio stream 314 may be in a language that represents words and/or numbers, so processor 318 translates the language into text that processor 318 understands. Response embodiments include performing a web search, dialing a phone number, opening an application, recording text, streaming media, composing text messages, listing journeys. , Or talking the journey. In a further embodiment, the processor 318 determines a response to present to the user of the computing device 300. Processor 318 may be similar in structure and function to processor 118 described in connection with FIG.

Processor 318 analyzes the digitized audio stream 314 stored in module 320. Embodiments of analysis module 320 include transmitting digitized audio stream 314 obtained from memory 314 to server 326. Other embodiments of module 320 include converting digitized audio stream 314 obtained from memory 312 into text stream 324 and sending text stream 324 to server 326. Other embodiments of module 320 include converting digitized audio stream 314 to text stream 324 to determine the appropriate response by analyzing the context of audio stream 302. For example, the digitized audio stream 314 can be converted at module 320 into a text stream 324 and a processor 318 within the text stream 324 to determine an appropriate response based on the context of the audio stream 302. Natural language processing may be utilized to analyze the text.

Text stream 324 includes text to determine the appropriate response for computing device 300. In one embodiment, the text stream 324 is processed by the processor at the output device 328 to determine the appropriate response to present to the user of the computing device 300. In another embodiment, text stream 324 is processed by server 326 to determine the appropriate response to send to computing device 300. In this embodiment, the response is sent from server 326 to computing device 300. In a further embodiment, computing device 300 presents a response to the user of computing device 300. For example, text stream 324 may include text that discusses sending a text message to a mother. Thus, the text in the text stream 324 commands the computing device 300 to respond by composing a text message to the mother.

Server 326 is suitable for providing services across a network and processing text stream 324 and sending responses to computing device 300, such as a web server, network server, local area network (LAN) server, file server. , Or any other computing device.

The output device 328 presents the response of the computing device 300 user determined from the text in the text stream 324. Embodiments of output device 328 include a display device, screen, or speaker for presenting a response to a user of computing device 300. Given the example of a text message to a mother, a user of computing device 300 may have a display that indicates that the text message to the mother is being created and/or a speaker to communicate the text message to the user. You can

Turning now to FIG. 4, a flowchart of an exemplary method performed at a computing device for receiving an audio stream and determining a response. 4 is described as being executed on computing device 100 as in FIG. 1, it can also be executed on other suitable components, as will be appreciated by those skilled in the art. For example, FIG. 4 may be implemented in the form of executable instructions on a machine-readable storage medium such as memory 112.

At operation 402, a computing device operating with a low power integrated circuit receives an audio stream. In one embodiment, the audio stream may be of a predetermined length of time. For example, the audio stream can be seconds or milliseconds. In this embodiment, the computing device may constantly monitor audio. In a further embodiment, the audio stream comprises at least one of speech from a user or audio from other computing devices.

At operation 404, the low power integrated circuit operating with the computing device digitizes the audio stream received at operation 402 to produce a digitized audio stream. Embodiments of operation 404 include the use of analog-to-digital converters (ADCs), digital conversion devices, instructions, firmware, and/or software that operate with low power integrated circuits. Embodiments of act 404 include sending the digitized audio stream to memory. While a further embodiment of 404 includes compressing the audio stream received at operation 402, another embodiment of 404 includes compressing the digitized audio stream.

At act 406, the digitized audio stream generated at act 404 is stored in memory. Embodiments of operation 406 include memory storing and/or maintaining a digitized audio stream. In another embodiment of act 406, the audio stream received during act 402 during the predetermined amount of time is digitized at act 404, eg, another audio stream is received at act 402 and at act 404. If digitized, this current digitized audio stream replaces the previous digitized audio stream. In this embodiment, the memory maintains the stored digitized audio stream received during the predetermined time period prior to the current time.

At operation 408, the low power integrated circuit analyzes the digitized audio stream generated at operation 404. While embodiments of act 408 include processing the digitized audio stream, other embodiments include comparing the digitized audio stream with keywords. In these embodiments of act 408, the low power integrated circuit processes the audio stream digitized for keywords. Once the keyword is recognized in the digitized audio stream, the method transitions to operation 410 for sending a signal. In a further embodiment, if the low power integrated circuit does not recognize the keyword in the digitized audio stream, the method returns to operation 402. Still a further embodiment includes comparing the digitized audio stream, a user analog or digital representation indicate that the desired response by the computing device of the computing device. In a further embodiment, operations 402, 404, 406, and 408 are also performed in parallel. For example, when the computing device analyzes the digitized audio stream at 408, the integrated circuit receives the audio stream at operation 402 and continues to digitize and store the audio stream at operations 404 and 406.

At operation 410, the low power integrated circuit sends a signal to the processor to increase power. In particular, when a keyword is recognized in the digitized audio stream, the low power integrated circuit signals the processor to increase the power. In an embodiment of operation 410, the processor increases power or electrical energy provided to the processor and/or computing device.

At operation 412, the processor obtains from memory the digitized audio stream stored at operation 406. In one embodiment of act 412, the memory sends the digitized audio stream to the processor, while in another embodiment of act 412, the processor retrieves the digitized audio stream from the memory.

At operation 414, the processor converts the digitized audio stream obtained at operation 412 into a text stream. After converting the digitized audio stream to a text stream, the processor analyzes the text in the text stream to determine an appropriate response. Embodiments of act 414 include using speech-to-text (STT), voice-to-text, digital-to-text, or other types of text conversion. A further embodiment of act 414 includes using natural language processing after conversion to a text stream. In this embodiment, the computing device processes the text in the text stream to determine an appropriate response based on the context of the audio stream received at operation 402. For example, upon detecting a keyword in the digitized audio stream at 408, the processor obtains the digitized audio stream at operation 412 and the digitized audio stream is converted to a text stream at operation 414. In a further example, the audio stream may include a conversation about a journey between two locations, eg, when the digitized audio stream is converted to a text stream in act 412, the processor may The appropriate response may be determined by analyzing the text.

At act 416, the processor determines a response based on the text stream generated at act 414. Response embodiments include performing a web search, dialing a phone number, opening an application, recording text, streaming media, composing text messages, listing journeys. , Or talking the journey. In one embodiment, the text in the text stream dictates the appropriate response for the processor. In a further embodiment, the response is presented to the user of the computing device. For example, the text stream may include a voice asking how to reach China, and thus the journey to China would be a suitable response. In addition, this example may include listing and/or speaking the journeys to China on a map display.

Referring now to FIG. 5, a flowchart of an exemplary method performed on a computing device to compress a digitized audio stream and present a response to a user of the computing device. Although FIG. 5 is described as being executed on the computing device 300 described above in FIG. 3, it can also be executed on other suitable components, as will be appreciated by those skilled in the art. For example, FIG. 5 may be implemented in the form of executable instructions on a machine-readable storage medium such as memory 312.

At operation 502, the computing device compresses the digitized audio stream. In one embodiment, act 502 is performed in conjunction with act 404 prior to act 406 in FIG. For example, as the received audio stream is digitized, a low power integrated circuit may work with the computing device to compress the digitized audio stream to reduce the data byte size of the stream. In this example, compression of the digitized audio stream is performed before it is stored in memory at operation 406. In a further embodiment, operation 502 is performed prior to receiving the digitized audio stream in operation 412 in FIG. For example, the processor may perform operation 502 to compress the digitized audio stream from the memory, while in another example, the memory may perform the digital operation before the processor obtains the digitized audio stream. The encrypted audio stream may be compressed. In yet another embodiment of act 502, the compressed digitized audio stream is analyzed to recognize keywords, as in step 408 in FIG.

At operation 504, the computing device presents a response to the user of the computing device. Embodiments of act 504 include what occurs during or after act 416 in FIG. For example, when the processor determines an appropriate response, this response may be presented to the user of the computing device. In a further embodiment, the response can be presented to the user on an output device such as a display screen or speaker that works with the computing device. For example, if the user is discussing the differences between shrimp and prawns, the processor may launch a web search application to perform, for example, a web search for shrimp versus prawns. The performed web search may be presented to the user on the display device of the computing device. In a further example, the computing device announces the difference between shrimp and prawns so that the user can hear them through a speaker. In these embodiments, the computing device operates such that the user uses the audio stream to determine the response, rather than instructing the computing device.

The embodiments described in detail herein digitize an audio stream to detect keywords, increase power, and further digitize based on recognition of keywords in the digitized audio stream. Signaling a processor to analyze an audio stream to determine a response. Thus, the exemplary embodiments save user time by reducing the power consumption of the computing device while preventing repeated voice commands to the computing device.
The inventions described in the claims at the initial application of the present application will be additionally described below.
[C1]
A method performed by a computing device including a low power integrated circuit and a processor, comprising:
Receiving an audio stream,
Digitizing the audio stream;
Storing the digitized audio stream in a memory;
Analyzing the digitized audio stream for keyword recognition using the low power integrated circuit;
Transmitting a signal from the low power integrated circuit to the processor to increase power when the keyword is recognized in the digitized audio stream;
Transmitting the stored digitized audio stream from the memory to the processor;
Converting the digitized audio stream into a text stream using the processor;
Determining a response for the processor based on the text stream;
A method comprising.
[C2]
Compressing the digitized audio stream into a compressed digitized audio stream
The method of C1, further comprising: analyzing the compressed digitized audio stream for recognition of the keyword.
[C3]
Presenting the response to the user of the computing device
The method according to C1, further comprising:
[C4]
The response is performing a web search, dialing a phone number, opening an application, recording text, streaming media, composing a text message, listing a route, or The method according to C3, comprising at least one of talking a journey.
[C5]
The method of C1, wherein the memory maintains the stored digitized audio stream received during a predetermined time period prior to the current time.
[C6]
Determining the response for the processor comprises
Receiving from the server the response based on the analysis of the text stream by the server;
Determining the response based on an analysis of the text stream by the processor;
The method according to C1, comprising one of:
[C7]
The method of C1, wherein the audio stream comprises at least one of a voice from a user, a voice from another computing device, and a voice from the another computing device.
[C8]
A computing device,
Upon receiving the audio stream, the audio stream is digitized and stored in memory, and the digitized audio stream is analyzed for keyword recognition,
Recognizing the keyword in the digitized audio stream sends a signal to the processor to increase power.
Low power integrated circuit for
Increasing power based on the signal from the low power integrated circuit,
Analyze the digitized audio stream to determine a response
With a processor for
A computing device comprising.
[C9]
To analyze the digitized audio stream, the processor further comprises:
Retrieving the digitized audio stream from the memory based on receiving a signal to increase the power,
Converting the digitized audio stream to a text stream,
Determine the response dictated by the text in the text stream
A computing device according to C8, which is for:
[C10]
To analyze the digitized audio stream, the processor further comprises:
Retrieving the digitized audio stream from the memory based on receiving a signal to increase the power,
Sending to the server the digitized audio stream or a text stream generated from the digitized audio stream to determine the response;
Receive the response from the server
A computing device according to C8, which is for:
[C11]
The low power integrated circuit further comprises:
Compressing the digitized audio stream to obtain a compressed digitized audio stream,
Analyze the compressed digitized audio stream to recognize the keywords
A computing device according to C8, which is for:
[C12]
An output device for presenting the response to a user of the computing device
The computing device according to C8, further comprising:
[C13]
The computing device of C8, wherein the low power integrated circuit compares the digitized voice stream with the keyword to analyze the digitized voice stream to recognize the keyword.
[C14]
A low power integrated circuit,
Receive an audio stream,
Digitize the audio stream,
Storing the digitized audio stream in memory,
Comparing the digitized audio stream with keywords,
For instructing a processor of a computing device to increase power and analyze the stored digitized voice stream from the memory when the keyword is recognized in the digitized voice stream. Send the signal of
Circuit elements for
A low power integrated circuit comprising:
[C15]
The low power integrated circuit of C14, wherein the memory maintains the stored digitized audio stream for a predetermined time period.

Claims (27)

A method for processing audio information , comprising:
Receiving an audio stream by a computing device, the audio stream including keywords and additional audio,
Monitoring the audio stream by a low power integrated circuit of the computing device ;
Digitizing the audio stream by the low power integrated circuit, the digitized audio stream including the keyword and the additional audio;
Storing the digitized audio stream in a memory within the computing device, wherein storing the digitized audio stream is the same as the previous digitized audio stored in the memory. Comprising replacing a stream with the digitized audio stream,
Analyzing the stored digitized audio stream for recognition of the keyword by the low power integrated circuit;
If you recognize the keyword in the stored digitized in the voice stream, wherein the low-power integrated circuits, processors of the computing device, to enter a power use state increased, and the memory from the memory Causing at least said additional audio of a digitized audio stream of audio,
Obtaining at least the additional audio of the stored digitized audio stream from the memory by the processor;
At least the addition of the stored digitized audio stream by the computing device to determine one or more actions based on at least the additional audio of the stored digitized audio stream. Sending audio to the server,
Rendering the response received by the computing device from the server, wherein the response is based on an analysis of at least the additional audio of the digitized audio stream, the one or more actions. Comprising one or more instructions for executing
A method comprising. The method of claim 1, wherein the stored digitized audio stream is converted to a text stream . The one or more instructions perform a web search, dial a phone number, open an application, record text, stream media, compose a text message, list a route displaying, or to speak journey, comprises at least one of the method of claim 1. The method of claim 1, wherein the audio stream comprises at least one of a voice from a user, a voice from another computing device, or a voice from the other computing device. The method of claim 1, further comprising compressing the digitized audio stream prior to storage in the memory. In response to recognizing the keyword in the stored digitized audio stream,
Constantly receiving the audio stream;
Constantly monitoring the audio stream;
Constantly digitizing the audio stream;
The method of claim 1, further comprising: The method of claim 1, further comprising outputting the rendered response by at least one of a display of the computing device or a speaker of the computing device. The method of claim 1, wherein receiving the audio stream comprises receiving the audio stream from a user by a microphone of the computing device. A computing device for processing audio information , comprising:
A low power integrated circuit,
A memory coupled to the low power integrated circuit,
A processor coupled to the low power integrated circuit and the memory, the low power integrated circuit comprising:
Monitoring and digitizing an audio stream received by the computing device, the digitized audio stream including keywords and additional audio;
Storing the digitized audio stream in the memory, wherein storing the digitized audio stream includes converting the previous digitized audio stream stored in the memory to the digital Comprising replacing the encrypted audio stream,
Analyzing the stored digitized audio stream to recognize the keyword;
Recognizing the keyword in the stored digitized audio stream causes the processor of the computing device to enter an increased power usage state and the stored digitized audio stream from the memory. Causing at least the additional audio of
Is configured to
The processor is
Obtaining at least the additional audio of the stored digitized audio stream from the memory;
Transmitting at least the additional audio of the stored digitized audio stream to a server to determine one or more actions based on at least the additional audio of the stored digitized audio stream. That
Rendering a response received by the computing device from a server, wherein the response is based on an analysis of at least the additional audio of the digitized audio stream,
A computing device configured to perform. The computing device of claim 9, wherein the stored digitized audio stream is converted into a text stream. The computing device of claim 9, wherein the response received from the server comprises one or more instructions for performing the one or more actions by the processor. The one or more instructions perform a web search by the processor, dial a telephone number, open an application, record text, stream media, compose a text message, The computing device of claim 11, comprising at least one of listing a journey or speaking a journey. The computing device of claim 9, wherein the audio stream comprises at least one of a voice from a user, a voice from another computing device, or a voice from the another computing device. The computing device of claim 9, wherein the digitized audio stream is compressed prior to storage in the memory. The low power integrated circuit is responsive to recognizing the keyword in the stored digitized audio stream,
Constantly receiving the audio stream;
Constantly monitoring the audio stream;
Constantly digitizing the audio stream;
The computing device of claim 9, further configured to: A display configured to output the rendered response, or
A speaker configured to output the rendered response
The computing device of claim 9, further comprising at least one of: The computing device of claim 9, wherein the received audio stream is received by a microphone of the computing device. The processor is
Sending the keyword and the additional audio of the stored digitized audio stream to the server to determine the one or more actions.
The computing device of claim 9, further configured to: A system for analyzing a digitized audio stream, comprising:
One or more processors,
Memory and
A low power integrated circuit coupled to the one or more processors and the memory;
And a low power integrated circuit comprising:
Monitoring and digitizing an audio stream received by the computing device, the digitized audio stream including keywords and additional audio;
Storing the digitized audio stream in the memory;
Analyzing the stored digitized audio stream to recognize the keyword;
Recognizing the keyword in the stored digitized audio stream causes the one or more processors to enter an increased power usage state.
Is configured to
Server and
And the server is
Receiving at least the additional audio of the digitized audio stream transmitted from the computing device;
Processing at least the additional audio of the received digitized audio stream to determine one or more actions;
Sending instructions to the computing device to perform the one or more actions, wherein the instructions are based on an analysis of at least the additional audio of the received digitized audio stream. ,
A system configured to perform. 20. The system of claim 19, wherein the one or more processors are further configured to perform the one or more actions based at least in part on the instructions received from the server. The one or more actions are performing a web search, dialing a phone number, opening an application, recording text, streaming media, composing a text message, listing a journey 21. The system of claim 20, comprising at least one of displaying or speaking a journey. 20. The system of claim 19, wherein the one or more processors are further configured to send at least the additional audio of the digitized audio stream to the server. 23. The system of claim 22, wherein the one or more processors are further configured to compress the digitized audio stream. 20. The system of claim 19, wherein the received audio stream is received by a microphone of the computing device. 20. The system of claim 19, wherein the low power integrated circuit is further configured to replace a previous digitized audio stream stored in the memory with the digitized audio stream. The computing device is
A display configured to output the rendered response, or
A speaker configured to output the rendered response
20. The system of claim 19, further comprising at least one of: In order to process the received digitized audio stream, the server is
Converting the received digitized audio stream into a text stream;
Analyzing the text stream to determine the meaning of the text stream;
20. The system of claim 19, further configured to:

Images