CN103390410A - Telephone conference system and method - Google Patents

Abstract

The invention provides a remote telephone conference system and a method, wherein the system comprises: a far-end microphone array for receiving far-end sound; a voice identification module for identifying a plurality of sound sources from the remote voice; a near-end display interface for displaying the plurality of sound sources; and the sound adjusting module is used for adjusting a sound characteristic of each sound source respectively. The invention can visualize the spatial position of the far-end conference participants, is more beneficial to the near-end conference participants to know the seat relationship of the far-end conference participants compared with the prior art, and provides a basis for adjusting sound parameters so as to achieve the purpose of improving the quality of the remote telephone conference.

Description

Telephone conference system and method

technical field

The invention relates to teleconferencing technology.

Background technique

The teleconferencing system is a common means of communication in business offices, which enables two parties, three parties, or even multiple parties to communicate without geographical restrictions.

In a teleconference, as far as both parties are concerned, there may be more than one participant at the far or near end. Some conferencing systems will configure dedicated microphones for each participant. Although this can ensure that the speech of each participant can be received, the authentication procedure and conference management mechanism are more complicated; in addition, when the participants When the number of microphones increases, the demand for the number of microphones will increase, and the sound interference between adjacent microphones will become more serious. In order to facilitate the erection of the conference call system, most conference calls do not configure a dedicated microphone for each participant, but let all participants share the same microphone. However, limited by the arrangement of the seats, when the distance between the participants and the microphone is different, the sound collection effect of the microphone will also be different, which will impair the quality of the conversation between the two parties.

Therefore, a more convenient and easy-to-use teleconferencing system and method are needed.

Contents of the invention

In order to overcome the defects of the prior art, the present invention provides a teleconferencing system, which includes: a remote microphone array, arranged at the far end, to receive the sound from the far end; a sound recognition module, coupled to the far end A microphone array, used to identify multiple sound sources from far-end sounds; a near-end display interface, set at the near end, coupled to the sound recognition module, for displaying the multiple sound sources identified by the sound recognition module a sound source; a sound adjustment module, coupled to the sound recognition module, for adjusting a sound feature of each of the sound sources.

The present invention also provides a method for teleconferencing, which includes: receiving far-end sound with a far-end microphone array; identifying multiple sound sources from the far-end sound; and displaying the identified multiple sound sources with a near-end display interface. sound sources; adjusting at least one sound characteristic of each of the sound sources.

The present invention can visualize the spatial position of the far-end participants. Compared with the prior art, it is more helpful for the near-end participants to understand the seat relationship of the far-end participants, thereby providing a basis for adjusting sound parameters. To achieve the purpose of improving the quality of remote teleconferencing.

Description of drawings

FIG. 1 is a schematic diagram of a teleconferencing system architecture according to an embodiment of the present invention.

FIG. 2 is a flow chart of a teleconferencing method according to an embodiment of the present invention.

Wherein, the reference signs are explained as follows:

100~ remote teleconferencing system;

102~far-end microphone array;

104~sound recognition module;

106~proximal display interface;

108~ near-end control interface;

110~sound adjustment module;

112~sound playback module;

S202~S210~steps.

Detailed ways

The following describes the preferred embodiment of the present invention. Each embodiment is used to illustrate the principles of the present invention, but not to limit the present invention. The scope of the present invention should be determined by the appended claims.

In order to make the teleconferencing system easier to use, the present invention provides a novel teleconferencing system. Various embodiments of the teleconferencing system of the present invention will be described below with reference to the accompanying drawings.

teleconferencing system

FIG. 1 is a schematic diagram of a teleconferencing system architecture according to an embodiment of the present invention. The teleconferencing system 100 of the present invention at least includes: a remote microphone array 102 , a sound recognition module 104 , a near-end display interface 106 , a near-end control interface 108 , a sound adjustment module 110 and a sound playback module 112 . For the convenience of description, the following embodiments all take one-way communication as an example (that is, the far-end user speaks, and the near-end user listens). The invention is applied to two-way communication. Similarly, the present invention is not limited to the types of two-party calls, and the types of multi-party calls are also within the scope of the present invention.

The far-end microphone array 102 of the present invention is set at the far end and can be used to receive far-end sound. Generally speaking, the microphone array 102 usually includes two or more microphones. The microphone of the present invention is not limited to dynamic, condenser, or other various types of microphones. Those skilled in the art can set the microphone array 102 at a proper position according to the number of microphones, the directivity of each microphone and the meeting space. For example, in a round table conference, a microphone array with omnidirectional sound field sensitivity can be used and placed at the center of the round table.

The sound recognition module 104 of the present invention is not limited to be disposed at the far end or near end, as long as it can be connected to the aforementioned far end microphone array 102 through wired or wireless communication. It is worth noting that the important feature of the present invention is that the voice recognition module 104 of the present invention can identify and separate multiple individual voices from the mixed far-end voices obtained by the microphone array 102 according to various existing acoustic calculation techniques. different sound sources. For example, these sound sources include voices of various participants and various non-speech noises. Generally speaking, acoustic calculation technology can be mainly divided into sound direction recognition technology and sound quality recognition technology. The sound direction recognition technology can utilize the position and sensitivity of each microphone in the microphone array 102 to calculate the direction and distance of each sound source (that is, the position of the sound source in space); and the sound quality recognition technology can analyze the sound pressure, frequency spectrum and Analyze the waveform to obtain the sound characteristics of each sound source such as volume, clarity, audio frequency and sound quality (or timbre), and even judge whether each sound source is speech or noise, and estimate the approximate gender and age of the speaker . In more detail, since speech is not a continuous sound, and its volume and audio frequency may change, therefore, in a better embodiment, the sound recognition module 104 of the present invention can continuously cross compare a sound source in space position and its sound quality to achieve the purpose of tracking and locking the sound source. In addition, in some embodiments, the sound recognition module 104 can also perform general noise filtering and echo cancellation operations. However, since the above technical details of the sound processing are not the focus of the present invention and can be achieved by various existing technologies, they are not repeated here to save space.

The near-end display interface 106 (i.e. screen) of the present invention is arranged at the near-end, and it is coupled to the voice recognition module 104, and can be used to display each sound source identified by the voice recognition module 104 to the near-end user. In some embodiments, various sound characteristics of the plurality of sound sources are displayed. For example, in a simplest embodiment, the near-end display interface 106 only displays the far-end sound sources recognized by the sound recognition module 104 in text, and respectively assigns each existing sound source such as "participant 1", " Participant 2" and so on. Whenever the voice recognition module 104 detects that a new member joins at the far end, the near-end display interface 106 can mark it with striking text. In a preferred embodiment, the near-end display interface 106 can simulate the far-end meeting space in two-dimensional or three-dimensional images, and mark them on the virtual screen according to the coordinates of the spatial positions of the sound sources detected by the voice recognition module 104 above the corresponding position. Among them, in addition to the names of "participant 1" and "participant 2", each sound source can also add various sound characteristics, such as: volume, clarity, audio, sound quality, whether it is voice, the gender and age of the speaker and related estimated information, those skilled in the art can design the information items displayed on the near-end display interface 106 and their display style according to the spirit of the present invention. It is worth noting that the teleconferencing technology of the present invention can also be further applied in video conferencing, and the near-end display interface 106 can also synchronously display the actual image transmitted from the far end instead of the aforementioned virtual image. Through the near-end display interface 106 of the present invention, the near-end user can easily grasp the situation of the far-end meeting.

The near-end control interface 108 of the present invention is coupled to the sound adjustment module 110 of the present invention, and can be used to receive the user's control on the sound adjustment module 110, and the sound adjustment module 110 of the present invention can recognize the sound according to the user's control Each sound source identified by the module 104 adjusts its sound characteristics respectively, and the sound characteristics include: volume, clarity, audio frequency and/or sound quality. For example, the near-end user can increase the volume of certain far-end important participants or improve their clarity by controlling the sound adjustment module 110; The voice sent out, thereby enhancing the call quality of the meeting. In some special embodiments, the sound adjustment module 110 can even perform various sound effect processing on each sound source, including changing its audio frequency or sound quality, so as to hide the speaker's identity. The sound adjustment module 110 of the present invention is not limited to be installed at the near end or the far end, as long as it can be connected to the sound recognition module 104 through wired or wireless means. In a preferred embodiment, the sound adjustment module 110 and the sound recognition module 104 can be integrated into a processor to achieve the purpose of enhancing sound processing performance.

Finally, the sound playing module 112 of the present invention is coupled to the near-end speaker, and can be used to play each sound source after the aforementioned sound characteristics are adjusted. The sound playing module 112 of the present invention is also not limited to being located at the near end or the far end, as long as it can be connected to the sound adjustment module 110 in a wired or wireless manner. In a preferred embodiment, the sound playing module 112 can also be integrated with the sound adjustment module 110 and the sound recognition module 104 into one processor. Those skilled in the art can understand that the difference between the voice recognition module 104 , the voice adjustment module 110 and the voice playback module 112 is only for convenience of description, and any processor with the functions of the aforementioned modules falls within the scope of the present invention.

Teleconferencing method

In addition to the aforementioned teleconferencing system, the present invention further provides a teleconferencing method. FIG. 2 is a flow chart of a teleconferencing method according to an embodiment of the present invention. The method 200 includes: in step S202, receiving far-end sound with a far-end microphone array; in step S204, identifying multiple sound sources from the far-end sound; in step S206, displaying the The identified plurality of sound sources and their sound characteristics; in step S208 , adjusting at least one sound characteristic of each of the sound sources; and in step S210 , playing the plurality of sound sources after adjusting the sound characteristics. Wherein, step S204 can identify the multiple sound sources from the remote sound through the sound direction recognition technology and/or sound quality recognition technology, and these sound features are the direction, distance, volume, clarity, audio and/or sound quality of each sound source. or sound quality. Since those skilled in the art can refer to the aforementioned various embodiments of the teleconferencing system to understand the teleconferencing method of the present invention, relevant details will not be repeated here to save space.

Although the present invention is disclosed above with preferred embodiments, it is not intended to limit the scope of the present invention. Anyone skilled in the art may make some changes and modifications without departing from the spirit and scope of the present invention. Therefore, the protection scope of the present invention should be determined by the scope defined by the appended claims.

Claims (11)

1. remote phone conference system comprises:

One voice recognition module, in order to receive a far-end sound that receives from a far-end microphone array, and pick out a plurality of sources of sound in this far-end sound certainly;

One near-end display interface, be coupled to this voice recognition module, in order to the described a plurality of sources of sound that show that this voice recognition module picks out; And

One sound adjusting module, be coupled to this voice recognition module, in order to adjust for a sound characteristic of this source of sound respectively respectively.

2. remote phone conference system as claimed in claim 1 also comprises:

One near-end is controlled interface, is coupled to this sound adjusting module, in order to receive the control of this user to this sound adjusting module.

3. remote phone conference system as claimed in claim 1 also comprises:

One sound broadcasting module, be coupled to this sound adjusting module, in order to the described a plurality of sources of sound after broadcast adjustment sound characteristic.

4. remote phone conference system as claimed in claim 1, wherein this voice recognition module is that one of them picks out described a plurality of source of sound from this far-end sound by audio direction identification technique and tonequality identification technique.

5. remote phone conference system as claimed in claim 1, wherein this near-end display interface is also in order to show the sound characteristic of described a plurality of sources of sound that this voice recognition module picks out.

6. remote phone conference system as claimed in claim 1, the sound characteristic of wherein said a plurality of sources of sound comprises direction and/or the distance of described a plurality of sources of sound.

7. remote phone conference system as claimed in claim 1, the sound characteristic of wherein said a plurality of sources of sound is volumes of described a plurality of sources of sound.

8. remote phone conference system as claimed in claim 1, the sound characteristic of wherein said a plurality of sources of sound comprises the sharpness of described a plurality of sources of sound, audio frequency and/or tonequality.

9. remote phone conference method comprises:

Receive a far-end sound of a far-end microphone array;

Pick out a plurality of sources of sound from this far-end sound; And

Show the described a plurality of sources of sound that picked out with a near-end display interface;

Adjust at least one sound characteristic of this source of sound respectively respectively.

10. remote phone conference method as claimed in claim 9 also comprises:

One of them picks out described a plurality of source of sound from this far-end sound by audio direction identification technique and tonequality identification technique.

11. remote phone conference method as claimed in claim 9, the sound characteristic of wherein said a plurality of sources of sound comprise the direction of described a plurality of sources of sound, distance, volume, sharpness, audio frequency and tonequality one of them.

Images