CN110427167B - Audio information processing method for handheld device - Google Patents
Audio information processing method for handheld device Download PDFInfo
- Publication number
- CN110427167B CN110427167B CN201910499687.0A CN201910499687A CN110427167B CN 110427167 B CN110427167 B CN 110427167B CN 201910499687 A CN201910499687 A CN 201910499687A CN 110427167 B CN110427167 B CN 110427167B
- Authority
- CN
- China
- Prior art keywords
- handheld device
- audio information
- horizontal plane
- handheld
- audio
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003672 processing method Methods 0.000 title abstract description 13
- 230000010365 information processing Effects 0.000 title abstract description 12
- 238000012545 processing Methods 0.000 claims abstract description 27
- 238000000034 method Methods 0.000 claims abstract description 25
- 230000008569 process Effects 0.000 claims abstract description 4
- 230000036544 posture Effects 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 3
- 238000013518 transcription Methods 0.000 description 3
- 230000035897 transcription Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C9/00—Measuring inclination, e.g. by clinometers, by levels
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/16—Sound input; Sound output
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72448—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions
- H04M1/72454—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions according to context-related or environment-related conditions
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
- G11B20/00—Signal processing not specific to the method of recording or reproducing; Circuits therefor
- G11B20/10—Digital recording or reproducing
- G11B20/10527—Audio or video recording; Data buffering arrangements
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
- G11B20/00—Signal processing not specific to the method of recording or reproducing; Circuits therefor
- G11B20/10—Digital recording or reproducing
- G11B20/10527—Audio or video recording; Data buffering arrangements
- G11B2020/10537—Audio or video recording
- G11B2020/10546—Audio or video recording specifically adapted for audio data
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Radar, Positioning & Navigation (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Remote Sensing (AREA)
- Environmental & Geological Engineering (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- User Interface Of Digital Computer (AREA)
- Machine Translation (AREA)
Abstract
The invention relates to a handheld device audio information processing method, a central processing unit sets one face of a handheld device as a positive direction according to an included angle between an attitude sensor and a horizontal plane, and judges whether the handheld device is in the positive direction or the negative direction; starting a corresponding audio processing engine according to the position of the handheld device; the handheld device collects audio information; the audio processing engine analyzes and processes the audio information; and storing the acquired audio information and the analyzed and processed audio information in a set storage area. The invention discloses a handheld device audio information processing method, which ingeniously utilizes the characteristic that the handheld device points differently during dialogue, obtains the self-gesture of the handheld device by using an electronic gyroscope commonly applied by the handheld electronic device at present, judges the current sound acquisition object by a corresponding algorithm, and has the advantages of simple and ingenious conception, no need of a large amount of computing power, low cost and high accuracy.
Description
Technical Field
The invention relates to an audio processing method, in particular to an audio information processing method of handheld equipment.
Background
With the development of technology, more and more cases of recording or translating voice using handheld devices are required, and voice recognition technology is required. Under the condition that two persons talk, if the voice input by the current handheld device is what person in the conversation is said, the voice input by the current handheld device has great effect on the subsequent voice processing and subsequent processing, for example, in the use of a translator, if the person who inputs the voice at present is known, the language which he speaks can be judged according to the setting, recognition engines of different languages can be purposefully called, and more accurate recognition results can be obtained; for example, in the interview recording device, if the current recorded object is an interviewee or an interviewee, the results of speech recognition and transcription can be recorded in the records of the corresponding persons respectively, and if two persons have different local accents, the engines aiming at the different local accents can be called according to the setting, so that better recognition results can be obtained. Therefore, a method for distinguishing the current handheld device sound collection object is found, and the method has important practical value.
At present, some solutions are available to distinguish sound collection objects, one method is to add a hardware button or a software button on a handheld device, when recording, a specific key is set for a person, the sound of the person is recorded, the corresponding key is pressed, for example, a translator is used, the person presses the key to represent the person speaking, and the person presses the key to represent the person speaking; one method is to use software algorithm, design through artificial intelligence method, use voiceprint to distinguish which speaker is in the dialogue; one method is to automatically identify the language type spoken by the speaker, also by a software artificial intelligence algorithm.
The two methods are complex to operate, and a user must press a designated button each time of recording, so that the method is inconvenient to use; meanwhile, frequent operation also has the condition of misoperation, if the misoperation happens, the voice recognition engine can call the wrong recognition method, and the use accuracy is reduced.
The second artificial intelligence software algorithm is difficult to realize, has high technical threshold, consumes a large amount of computing power in computing, and has high misjudgment rate and is still immature.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides the handheld equipment audio information processing method which is simple and feasible, small in calculated amount, low in cost, high in accuracy and convenient to use.
The technical scheme adopted by the invention is as follows:
a method for processing audio information of a handheld device comprises the handheld device,
the handheld device acquires the gesture information of the handheld device through a gesture sensor, and determines the currently acquired voice as a corresponding acquisition object according to the gesture information of the handheld device;
and according to different collected objects, correspondingly processing the collected voice.
When the handheld device points to the user and points to the other side, the included angle between the pointing direction of the front surface of the handheld device and the horizontal plane is greatly changed; the attitude sensor is determined to be different collected objects through the change of the included angle between the pointing direction of the front face of the handheld device and the horizontal plane.
The handheld device is determined to be two postures through a posture sensor, and the two postures are respectively: the handheld device points towards each other and towards itself.
The attitude sensor is an electronic gyroscope or an electronic gyroscope chip.
Usually when a user uses a sound collection handheld device, he speaks, the handheld device points to himself, the other party speaks, and the handheld device points to the other party.
The angle between the front direction of the handheld device and the horizontal plane is 0-90 degrees, which is the forward direction, and 90-180 degrees, which is the reverse direction.
The angle between the front direction of the handheld device and the horizontal plane is 0-80 degrees, which is the forward direction, and 80-180 degrees, which is the reverse direction.
A handheld device audio information processing method comprises the following steps:
step 1, a central processing unit sets one face of a handheld device as a positive direction according to an included angle between an attitude sensor and a horizontal plane, and sets one direction along the front face of the handheld device as a reverse direction;
step 2, starting the handheld device;
step 3, judging whether the handheld device is in the forward direction or the reverse direction;
step 4, starting a corresponding audio processing engine according to the position of the handheld device;
step 5, the handheld device collects audio information;
step 6, the audio processing engine analyzes and processes the audio information;
step 7, storing the collected audio information and the analyzed and processed audio information in a set storage area;
step 8, judging whether the information collection of the handheld device is finished or not, and executing the step 3 if the information collection is not finished; the acquisition is finished and the step 9 is executed;
and 9, ending.
The angle may be expressed as a negative number or may be reversed with respect to the two objects defined above, depending on the definition of the front of the device.
The handheld device points to itself and points to the other side, the angle range of the front face of the device and the horizontal plane is quite different, and the current sound collection object is judged to be one of the two sides by defining the angle ranges of the front faces of different handheld devices and the horizontal plane.
The method for processing the audio information of the handheld device can realize the distinction of two dialogue roles in many occasions by combining with the prior convention, including but not limited to the use in interview recorders, translators and mobile phones.
The method for processing the audio information of the handheld device can distinguish the object for collecting the sound, further determine the information such as accent, language, name and the like of the object for collecting the sound according to the convention, and facilitate the subsequent speech recognition and transcription.
Compared with the prior art, the invention has the beneficial effects that:
the invention discloses a handheld device audio information processing method, which ingeniously utilizes the characteristic that the handheld device points differently during dialogue, obtains the self-gesture of the handheld device by using an electronic gyroscope commonly applied by the handheld electronic device at present, judges the current sound acquisition object by a corresponding algorithm, and has the advantages of simple and ingenious conception, no need of a large amount of computing power, low cost and high accuracy.
Drawings
FIG. 1 is an audio processing flow chart of a handheld device audio information processing method of the present invention;
FIG. 2 is a schematic diagram of the use status of the method for processing audio information of a handheld device according to the present invention;
FIG. 3 is a schematic diagram of the handheld device usage orientation of the handheld device audio information processing method of the present invention.
The main component symbols in the drawings illustrate:
Detailed Description
The invention is described in detail below with reference to the attached drawings and examples:
as can be seen from fig. 1-3, a method for processing audio information of a handheld device, comprising a handheld device,
the handheld device acquires the gesture information of the handheld device through a gesture sensor, and determines the currently acquired voice as a corresponding acquisition object according to the gesture information of the handheld device;
and according to different collected objects, correspondingly processing the collected voice.
When the handheld device points to the user and points to the other side, the included angle between the pointing direction of the front surface of the handheld device and the horizontal plane is greatly changed; the attitude sensor is determined to be different collected objects through the change of the included angle between the pointing direction of the front face of the handheld device and the horizontal plane.
The handheld device is determined to be two postures through a posture sensor, and the two postures are respectively: the handheld device points towards each other and towards itself.
The attitude sensor is an electronic gyroscope or an electronic gyroscope chip.
Usually when a user uses a sound collection handheld device, he speaks, the handheld device points to himself, the other party speaks, and the handheld device points to the other party.
The angle between the front direction of the handheld device and the horizontal plane is 0-90 degrees, which is the forward direction, and 90-180 degrees, which is the reverse direction.
The angle between the front direction of the handheld device and the horizontal plane is 0-80 degrees, which is the forward direction, and 80-180 degrees, which is the reverse direction.
A handheld device audio information processing method comprises the following steps:
step 1, a central processing unit sets one face of a handheld device as a positive direction according to an included angle between an attitude sensor and a horizontal plane, and sets one direction along the front face of the handheld device as a reverse direction;
step 2, starting the handheld device;
step 3, judging whether the handheld device is in the forward direction or the reverse direction;
step 4, starting a corresponding audio processing engine according to the position of the handheld device;
step 5, the handheld device collects audio information;
step 6, the audio processing engine analyzes and processes the audio information;
step 7, storing the collected audio information and the analyzed and processed audio information in a set storage area;
step 8, judging whether the information collection of the handheld device is finished or not, and executing the step 3 if the information collection is not finished; the acquisition is finished and the step 9 is executed;
and 9, ending.
Depending on the definition of the front of the device, the angle may be expressed as a negative number or may be opposite to the two objects defined above.
The handheld device points to itself and points to the other side, the angle range of the front face of the device and the horizontal plane is quite different, and the current sound collection object is judged to be one of the two sides by defining the angle ranges of the front faces of different handheld devices and the horizontal plane.
The present invention, in combination with prior conventions, allows for the differentiation of two-person conversational characters in many applications, including but not limited to use in interview recorders, translators and cell phones.
The invention can distinguish the object for collecting the sound, further determine the information of accent, language, name and the like of the object for collecting the sound according to the convention, and is convenient for the subsequent voice recognition and transcription.
The method has the advantages of simplicity, easiness, small calculated amount, high accuracy and convenience in use; under the condition of not influencing the behavior habit of the user, the current sound collection object can be accurately judged to be one of the two parties without very accurately measuring the gesture of the handheld device. Similarly, if the method is used for a translator, after the languages of the two selected parties are selected, the current gesture of the translator can also be used for judging the speaking object to be the person, so that the language of the speaking object is known, and the corresponding voice recognition engine can be conveniently called in the later voice recognition.
At present, many handheld devices are provided with electronic gyroscope chips, most of common mobile phones are provided with electronic gyroscope chips, and the included angle between the front surface of the handheld device and the horizontal plane can be conveniently obtained. For example, using an android mobile phone, the angle between the front surface of the mobile phone and the horizontal plane can be calculated and obtained by calling a sensor manager.
The invention skillfully utilizes the habit of holding the sound collection equipment by the human and utilizes the electronic gyroscope chip, thereby simply, efficiently and cheaply completing the problem of distinguishing the speakers between two people, which is not easy to solve by an artificial intelligent algorithm.
The invention is used for interview recording pens, translators and other devices, can greatly improve the use experience of users and increase the added value of products.
Compared with the prior art, the invention has the beneficial effects that:
the invention discloses a handheld device audio information processing method, which ingeniously utilizes the characteristic that the handheld device points differently during dialogue, obtains the self-gesture of the handheld device by using an electronic gyroscope commonly applied by the handheld electronic device at present, judges the current sound acquisition object by a corresponding algorithm, and has the advantages of simple and ingenious conception, no need of a large amount of computing power, low cost and high accuracy.
The above description is only of the preferred embodiment of the present invention, and is not intended to limit the structure of the present invention in any way. Any simple modification, equivalent variation and modification of the above embodiments according to the technical substance of the present invention fall within the technical scope of the present invention.
Claims (4)
1. A method for processing audio information of a handheld device comprises the handheld device and is characterized in that,
the handheld device acquires the gesture information of the handheld device through a gesture sensor, and determines the currently acquired voice as a corresponding acquisition object according to the gesture information of the handheld device;
according to different collected objects, correspondingly processing collected voices;
the attitude sensor determines different collected objects through the change of the included angle between the pointing direction of the front surface of the handheld device and the horizontal plane;
the handheld device is determined to be two postures through a posture sensor, and the two postures are respectively: the handheld device points to the other party and points to the person;
the method comprises the following steps:
step 1, a central processing unit sets one face of a handheld device as a positive direction according to an included angle between an attitude sensor and a horizontal plane, and sets one direction along the front face of the handheld device as a reverse direction;
step 2, starting the handheld device;
step 3, judging whether the handheld device is in the forward direction or the reverse direction;
step 4, starting a corresponding audio processing engine according to the position of the handheld device;
step 5, the handheld device collects audio information;
step 6, the audio processing engine analyzes and processes the audio information;
step 7, storing the collected audio information and the analyzed and processed audio information in a set storage area;
step 8, judging whether the information collection of the handheld device is finished or not, and executing the step 3 if the information collection is not finished; the acquisition is finished and the step 9 is executed;
and 9, ending.
2. The method for processing audio information of a handheld device according to claim 1, wherein:
the attitude sensor is an electronic gyroscope or an electronic gyroscope chip.
3. The method for processing audio information of a handheld device according to claim 1, wherein:
the angle between the front direction of the handheld device and the horizontal plane is 0-90 degrees, which is the forward direction, and 90-180 degrees, which is the reverse direction.
4. The method for processing audio information of a handheld device according to claim 1, wherein:
the angle between the front direction of the handheld device and the horizontal plane is 0-80 degrees, which is the forward direction, and 80-180 degrees, which is the reverse direction.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910499687.0A CN110427167B (en) | 2019-06-11 | 2019-06-11 | Audio information processing method for handheld device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910499687.0A CN110427167B (en) | 2019-06-11 | 2019-06-11 | Audio information processing method for handheld device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110427167A CN110427167A (en) | 2019-11-08 |
CN110427167B true CN110427167B (en) | 2024-01-02 |
Family
ID=68408572
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910499687.0A Active CN110427167B (en) | 2019-06-11 | 2019-06-11 | Audio information processing method for handheld device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110427167B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111143605A (en) * | 2019-12-30 | 2020-05-12 | 秒针信息技术有限公司 | Voice separation method and device and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104851446A (en) * | 2014-02-17 | 2015-08-19 | 拓集科技股份有限公司 | voice management method and system |
CN105100413A (en) * | 2015-05-27 | 2015-11-25 | 努比亚技术有限公司 | Information processing method, device and terminal |
CN105554201A (en) * | 2015-07-31 | 2016-05-04 | 宇龙计算机通信科技(深圳)有限公司 | Audio frequency circuit selection method, apparatus, and circuit, and hand-held terminal |
CN105554231A (en) * | 2015-07-31 | 2016-05-04 | 宇龙计算机通信科技(深圳)有限公司 | Voice communication method and apparatus |
CN105554230A (en) * | 2015-07-31 | 2016-05-04 | 宇龙计算机通信科技(深圳)有限公司 | Voice communication circuit and hand-held terminal |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5227736B2 (en) * | 2008-10-17 | 2013-07-03 | 三洋電機株式会社 | Recording device |
TWI502487B (en) * | 2013-10-24 | 2015-10-01 | Hooloop Corp | Methods for voice management, and related devices and computer program prodcuts |
-
2019
- 2019-06-11 CN CN201910499687.0A patent/CN110427167B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104851446A (en) * | 2014-02-17 | 2015-08-19 | 拓集科技股份有限公司 | voice management method and system |
CN105100413A (en) * | 2015-05-27 | 2015-11-25 | 努比亚技术有限公司 | Information processing method, device and terminal |
WO2016188379A1 (en) * | 2015-05-27 | 2016-12-01 | 努比亚技术有限公司 | Information processing method and device, terminal, and storage medium |
CN105554201A (en) * | 2015-07-31 | 2016-05-04 | 宇龙计算机通信科技(深圳)有限公司 | Audio frequency circuit selection method, apparatus, and circuit, and hand-held terminal |
CN105554231A (en) * | 2015-07-31 | 2016-05-04 | 宇龙计算机通信科技(深圳)有限公司 | Voice communication method and apparatus |
CN105554230A (en) * | 2015-07-31 | 2016-05-04 | 宇龙计算机通信科技(深圳)有限公司 | Voice communication circuit and hand-held terminal |
Also Published As
Publication number | Publication date |
---|---|
CN110427167A (en) | 2019-11-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110310623B (en) | Sample generation method, model training method, device, medium, and electronic apparatus | |
US9293133B2 (en) | Improving voice communication over a network | |
CN108363706B (en) | Method and device for man-machine dialogue interaction | |
US10013977B2 (en) | Smart home control method based on emotion recognition and the system thereof | |
DE112014000709B4 (en) | METHOD AND DEVICE FOR OPERATING A VOICE TRIGGER FOR A DIGITAL ASSISTANT | |
USRE44418E1 (en) | Techniques for disambiguating speech input using multimodal interfaces | |
WO2016150001A1 (en) | Speech recognition method, device and computer storage medium | |
CN108346425B (en) | Voice activity detection method and device and voice recognition method and device | |
JP2020515877A (en) | Whispering voice conversion method, device, device and readable storage medium | |
CN106971723A (en) | Method of speech processing and device, the device for speech processes | |
CN104090652A (en) | Voice input method and device | |
CN103391347A (en) | Automatic recording method and device | |
CN109032345B (en) | Equipment control method, device, equipment, server and storage medium | |
KR101559364B1 (en) | Mobile apparatus executing face to face interaction monitoring, method of monitoring face to face interaction using the same, interaction monitoring system including the same and interaction monitoring mobile application executed on the same | |
CN109101663A (en) | A kind of robot conversational system Internet-based | |
US20180054688A1 (en) | Personal Audio Lifestyle Analytics and Behavior Modification Feedback | |
CN110706707B (en) | Method, apparatus, device and computer-readable storage medium for voice interaction | |
Nishimura et al. | Versatile recognition using Haar-like feature and cascaded classifier | |
CN114360527A (en) | Vehicle-mounted voice interaction method, device, equipment and storage medium | |
CN110427167B (en) | Audio information processing method for handheld device | |
CN111583923A (en) | Information control method and device, and storage medium | |
CN108648754A (en) | Sound control method and device | |
Starner | The role of speech input in wearable computing | |
CN108510981B (en) | Method and system for acquiring voice data | |
JP2020067562A (en) | Device, program and method for determining action taking timing based on video of user's face |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |