CN208000739U - Optimized for external voice signaling devices - Google Patents

Abstract

A device capable of optimizing external voice signals comprises: a sound receiving unit, an analog-to-digital unit, a voice recognition unit, a voice processing unit, a digital-to-analog unit and an output unit. The sound receiving unit receives an external voice signal, and after being processed by the analog-to-digital unit, the voice recognition unit synthesizes and outputs a synthetic voice signal. When the voice recognition unit outputs a synthetic voice signal, the external voice signal is output simultaneously. After the voice processing unit receives the external voice signal and the synthetic voice signal, the voice processing unit adjusts the external voice signal according to the synthetic voice signal so that the external voice signal is the same as the synthetic voice signal, that is, outputs a clear voice signal. After being processed by the digital-to-analog unit, the output unit outputs a clear voice signal.

Description

Optimized for external voice signaling devices

technical field

The utility model relates to a speech recognition device, in particular to a speech signal device capable of optimizing external speech signals so that listeners can clearly hear the speech content.

Background technique

In the process of talking between people, the most fearful thing is that the surrounding environment is noisy, the pronunciation is not accurate or the speech is too fast, and the pronunciation of several words in a sentence is often unclear, resulting in the inability to understand the content or meaning of the speech , so often ask the other party or yourself to say it again, so that the other party or yourself can understand the content of the sentence.

Although, in the course of a conversation, if the environment is noisy, the pronunciation is not accurate, or the person who speaks too fast will make the other party not understand the meaning of certain words in a sentence, you can ask the other party to say it again, or Listening carefully can clarify the pronunciation of a few words that were just unclear to understand the semantic content. These are for people with sound hearing. However, for the hearing-impaired person, even if there is no environmental noise interference, or the person who speaks slowly, or the pronunciation of the voice is slightly inaccurate (acceptable range for the normal hearing person), the hearing-impaired person will be able to understand certain parts of a sentence. Even if you repeat the pronunciation of a word, the hearing-impaired person will still have the semantic confusion of a few words, so the hearing-impaired person will not understand the content of the other party's speech.

Utility model content

Therefore, the main purpose of the present utility model is to solve the traditional deficiency and provide an external voice signal device that can be optimized. The utility model is a voice signal device capable of optimizing external voice signals, adjusting the pitch of certain words in a sentence, and allowing listeners to clearly hear the voice content.

In order to achieve the above object, the utility model provides an external voice signal device that can be optimized, including: a radio unit, an analog-to-digital unit, a voice recognition unit, a voice processing unit, a digital-to-analog unit and an output unit. The sound receiving unit is used for receiving external voice signals. The analog-to-digital unit is electrically connected to the radio unit, and is used for converting the analog signal output by the radio unit into a digital signal for output. The voice recognition unit is electrically connected to the analog-to-digital unit to receive the external voice signal output by the analog-to-digital unit, and compares the external voice signal with the stored vocabulary data to synthesize and output a synthesized voice signal , when the voice recognition unit outputs a synthesized voice signal, it also outputs an external voice signal at the same time. The speech processing unit is electrically connected with the speech recognition unit, and is used to receive the external speech signal and the synthesized speech signal output by the speech recognition unit, and the speech processing unit adjusts the original input signal according to the synthesized speech signal. For the external voice signal, the wave envelope of the originally input external voice signal is the same as the wave envelope of the synthesized voice signal, and a clear voice signal is output after adjustment. The digital-to-analog unit is electrically connected to the voice processing unit, and is used for receiving the digital signal output by the voice processing unit and converting it into an analog signal for output. The output unit is electrically connected with the digital-to-analog unit, and is used for playing the voice signal output by the digital-to-analog unit.

In an embodiment of the present invention, the sound receiving unit is composed of one or more microphones.

In an embodiment of the present invention, the voice recognition unit at least includes a microprocessor, a temporary memory and a vocabulary memory.

In one embodiment of the present invention, the vocabulary memory is used to store vocabulary data, and when the voice recognition unit receives the external voice signal, the microprocessor will temporarily store the input external voice signal in the temporary memory In order to compare the vocabulary contained in the external speech signal with the data stored in the built-in vocabulary memory, and then according to the recognized sentence, the built-in vocabulary memory of the index can synthesize and output a Synthesize the speech signal.

In an embodiment of the present invention, the voice processing unit at least includes a microprocessor and a temporary memory for storing the adjusted voice.

In one embodiment of the present invention, the output unit is a speaker.

Description of drawings

Fig. 1 is a circuit block diagram of the voice signal device of the present invention.

FIG. 2 is a schematic diagram of the signal processing output of the circuit block of the speech signal device in FIG. 1 .

FIG. 3a is a schematic diagram of the external original voice signal waveform in FIG. 2 .

FIG. 3b is a schematic diagram of the synthesized speech signal waveform in FIG. 2 .

FIG. 3c is a schematic diagram of the clear voice signal waveform in FIG. 2 .

Explanation of symbols in the figure:

Radio unit 1

Analog to Digital Unit 2

Speech Recognition Unit 3

Microprocessor 31

scratch memory 32

Vocabulary memory33

Speech Processing Unit 4

microprocessor 41

scratch memory 42

Digital to Analog Unit 5

output unit 6

External voice signal A

Synthesized Speech Signal B

Clear speech signal C.

Detailed ways

Relevant technical content and detailed description of the present utility model, cooperate drawing description now as follows:

Please refer to FIG. 1 , which is a schematic block diagram of the circuit of the voice signal device of the present invention. As shown in the figure: the external voice signal device of the utility model can be optimized, including: a radio unit 1, an analog to digital unit (A/D) 2, a voice recognition unit 3, a voice processing unit 4, a digital Transfer to analog unit (D/A) 5 and an output unit. Wherein, when the sound receiving unit 1 receives an external voice signal, it can be recognized by the voice recognition unit 3 to identify the voice content, and adjust the original voice signal by the recognized voice content to make the voice signal clearer.

The sound receiving unit 1 is used for receiving external voice signals. In this figure, the radio unit 1 is composed of one or more microphones.

The analog-to-digital unit 2 is electrically connected to the radio unit 1 for receiving the analog signal output by the radio unit 1 and converting it into a digital signal for output.

The voice recognition unit 3 is electrically connected to the analog-to-digital conversion unit 2 , and the voice recognition unit 3 at least includes a microprocessor 31 , a temporary memory 32 and a vocabulary memory 33 . The vocabulary memory 33 is used to store vocabulary data (pronunciation and pitch data of characters, numbers or symbols). When the voice recognition unit 3 receives the external voice signal output by the analog-to-digital unit 2, the microprocessor 31 temporarily stores the input voice signal in the temporary memory 32, so that the external voice signal includes The vocabulary is compared with the data stored in the built-in vocabulary memory 33 to achieve the function of speech recognition. Then, according to the recognized sentence, the built-in vocabulary memory 33 of the index can be synthesized and estimated to output an ideal synthesized speech signal. When the speech recognition unit 3 outputs a synthesized speech signal, the external speech is also simultaneously The signal is output together.

The speech processing unit 4 is electrically connected with the speech recognition unit 3 . The speech processing unit 4 at least includes a microprocessor 41 and a temporary memory 42 for storing the adjusted speech. After the speech processing unit 4 receives the external speech signal and the synthesized speech signal output by the speech recognition unit 3, the microprocessor 41 inside the speech processing unit 4 will adjust the wave envelope according to the synthesized speech signal. The wave envelope of the original input external voice signal is made to be the same as the wave envelope of the synthesized voice signal, and a voice signal with good clarity is output after adjustment.

The digital-to-analog unit 5 is electrically connected to the voice processing unit 4 for receiving the output clear voice signal and converting it into an analog signal for output.

The output unit 6 is electrically connected with the digital-to-analog unit 5 . It is used to play the analog signal output by the digital-to-analog unit 5, so that the user can hear the clear voice signal. In this figure, the output unit 6 is a speaker.

Please refer to FIG. 2 and schematic diagrams of signal processing output, external voice signal waveform, synthesized voice signal waveform and clear voice signal waveform in the voice signal device circuit block in FIGS. 3a-3c. As shown in the figure: when receiving an external voice signal, the radio unit 1 of the voice signal device of the present utility model transmits the external voice signal to the analog-to-digital unit 2, converts the analog signal into a digital signal output, and then converts the analog signal to a digital signal. The converted digital signal is sent to the speech recognition unit 3, and the microprocessor 31 inside the speech recognition unit 3 temporarily stores the input speech signal in the temporary memory 32, so that the external speech signal A includes The vocabulary is compared with the data stored in the built-in vocabulary memory 33 to achieve the function of speech recognition. According to the identified sentence, the built-in vocabulary memory 33 of the index can be used to synthesize and estimate an ideal synthesized speech signal B, and when the speech recognition unit 3 outputs a synthesized speech signal B (as shown in Figure 3b) , and simultaneously output the external voice signal A (as shown in Fig. 3a).

The microprocessor 41 inside the voice processing unit 4 will adjust the original input external voice signal A according to the wave envelope of the synthesized voice signal B, so that the wave envelope of the original input external voice signal A can be close to the synthesized one. The wave envelope of the voice signal B is adjusted to output a voice signal C with good clarity.

Then, the digital signal of the clear voice signal C is converted into an analog signal for output, and the analog signal is played out by the output unit 6 so that the user can hear the clear voice signal.

For example, when A and B are talking, when B belongs to a hearing-impaired patient, B wears the earphone that can optimize the external voice signal device of the present utility model, and A says "what are you busy with today" to B? (When you are not wearing earphones), you may not be able to hear the word "busy" in this sentence, but you can clearly hear "what are you busy with today" in this sentence, but in After the second wears the earphone that can optimize the external voice signal device installed, this sentence can synthesize a relatively ideal "you are in today" after processing " busy " through the voice recognition unit 3 of the voice signal device of the present utility model What are you busy with” voice signal, and then through the voice processing unit 4 to adjust the original voice signal of “what are you busy with today” according to the synthesized voice signal of “what are you busy with today”, the speaker of the earphone will output a clear "What are you busy with today" voice signal, B can clearly hear what A is saying.

The above descriptions are only preferred embodiments of the present utility model, and are not intended to limit the scope of patent protection of the present invention. Therefore, all equivalent changes made by using the contents of the utility model specification or drawings are all included in the same reason. Within the protection scope of the utility model.

Claims (6)

1. An external voice signal device that can be optimized, is characterized in that, comprising: A radio unit for receiving external voice signals; An analog-to-digital unit, electrically connected to the radio unit, for converting the analog signal output by the radio unit into a digital signal for output; A voice recognition unit, electrically connected with the analog-to-digital unit, receives the external voice signal output by the analog-to-digital unit, compares the external voice signal with the stored vocabulary data, and outputs a synthesized When the voice recognition unit outputs a synthesized voice signal, an external voice signal is also output simultaneously; A speech processing unit, electrically connected to the speech recognition unit, used to receive the external speech signal output by the speech recognition unit and the synthesized speech signal, and adjust the original input external speech signal according to the synthesized speech signal , so that the wave envelope of the external voice signal originally input can be the same as the wave envelope of the synthesized voice signal, and a clear voice signal is output; A digital-to-analog unit, electrically connected to the speech processing unit, for receiving the signal output by the speech processing unit and converting it into an analog signal for output; An output unit is electrically connected with the digital-to-analog unit for playing the clear voice signal output by the digital-to-analog unit. 2. The external voice signal device that can be optimized according to claim 1, wherein the sound receiving unit is composed of one or more microphones. 3. The external speech signal device capable of optimizing as claimed in claim 1, wherein the speech recognition unit at least comprises a microprocessor, a temporary memory and a vocabulary memory. 4. The external speech signal device that can be optimized as claimed in claim 3, wherein the vocabulary memory is used to store vocabulary data, and when the speech recognition unit receives the external speech signal, the microprocessor will input the The external speech signal is temporarily stored in the temporary memory, so that the vocabulary contained in the external speech signal is compared with the data stored in the vocabulary memory, and then according to the recognized sentence, the Synthesize and output a synthesized speech signal by indexing the built-in vocabulary memory. 5. The external speech signal device capable of optimizing as claimed in claim 4, wherein the speech processing unit at least comprises a microprocessor and a temporary memory for storing the adjusted speech. 6. The external voice signal device capable of optimizing as claimed in claim 5, wherein the output unit is a speaker.