CN109979434A - The test method of local voice mould set product acoustical behavior - Google Patents
The test method of local voice mould set product acoustical behavior Download PDFInfo
- Publication number
- CN109979434A CN109979434A CN201910358064.1A CN201910358064A CN109979434A CN 109979434 A CN109979434 A CN 109979434A CN 201910358064 A CN201910358064 A CN 201910358064A CN 109979434 A CN109979434 A CN 109979434A
- Authority
- CN
- China
- Prior art keywords
- voice mould
- digital signal
- acoustical behavior
- test method
- standard
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/01—Assessment or evaluation of speech recognition systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
Abstract
A kind of test method of local voice mould set product acoustical behavior, includes the following steps: S1；Benchmark digital signal A1 is converted by fixed algorithm by analog audio signal A0；The fixed algorithm is analytical algorithm of the voice mould group to analog audio signal；S2；Analog audio signal A0 is inputted into voice mould group to be measured, voice mould group to be measured converts analog audio signal to and compares digital signal A2；S3；Benchmark digital signal A1 is compared with digital signal A2 is compared, judges that the acoustical behavior of voice mould group to be measured is up to standard if the two similarity reaches standard, it is otherwise not up to standard.Using the test method of local voice mould set product acoustical behavior of the present invention, it can fast and accurately judge that whether qualified the acoustical behavior of voice mould group is up to standard, the step process for reducing the test of mould group accelerates the time of mould group test, improves mould group testing efficiency.
Description
Technical field
The invention belongs to field of artificial intelligence, are related to speech recognition technology, and in particular to a kind of local voice mould group
The test method of product acoustical behavior.
Background technique
Speech recognition at present is widely used in each electronic product as a kind of common human-computer interaction technology, with
Its naturally convenient interactive mode has received liking for consumer, has been increasingly becoming the mainstream interactive controlling side in intellectual product epoch
Formula.
Speech recognition has a two class modes at present, and one kind is online free intercommunication mode, user using when can arbitrarily say
Words, collect user's speech content by product facility, upload to cloud server by network and carry out semantic analysis understanding, parsing
The purpose of user out, then progress corresponding operation control, this mode advantage in product facility are passed to by network and are user
It can freely talk, relatively daily life is accustomed to, but disadvantage is that network could use, and because being related to need
Voice data is uploaded, safety is poor, and in addition network has delay, and the product of Network Recognition needs to wait the knot of Network Recognition
Fruit needs the time spent with regard to more.
The shortcomings that in view of aforesaid way, the equipment such as current many functional product facilities such as air-conditioning, smoke exhaust ventilator are all
By the way of another kind of speech recognition, i.e., by the identification of offline voice control command word, carry out the function of product facility
Can control, such mode has many advantages, such as fast response time without using network, control it is simple, but need language has been previously set
Sound control command word, product facility can just respond after need to recognizing complete voice control command word, and set in actual product
It is the test of discrimination to the test mode of local voice mould set product acoustical behavior in standby application environment, this test method is deposited
The drawbacks such as not rigorous in standard, environment setting is complicated, and there are many time consumption.
Summary of the invention
To overcome technological deficiency of the existing technology, the invention discloses a kind of local voice mould set product acoustical behavioies
Test method.
The test method of local voice mould set product acoustical behavior of the present invention, includes the following steps:
S1；Benchmark digital signal A1 is converted by fixed algorithm by analog audio signal A0；The fixed algorithm is voice mould
Analytical algorithm of the group to analog audio signal；
S2；Analog audio signal A0 is inputted into voice mould group to be measured, analog audio signal is converted comparison by voice mould group to be measured
Digital signal A2；
S3；Benchmark digital signal A1 is compared with digital signal A2 is compared, judge if the two similarity reaches standard to
The acoustical behavior for surveying voice mould group is up to standard, otherwise not up to standard.
Preferably, the benchmark digital signal A1 and to compare digital signal A2 be standard iis digital signal.
Further, the clock frequency for being converted to standard iis digital signal is 1Mhz；Left and right alignment clock is 16Khz.
Preferably, the analog audio signal A0 is fixed frequency response curve.
Further: the analog audio signal A0 is frequency 1k hertz, the sine wave of amplitude 1V.
Preferably, the way of contrast in the step S3 is the monocycle pair that the clock cycle one by one is chronologically carried out to signal
Than being judged whether according to the ratio that the same period quantity detected accounts for complete signal clock cycle number up to standard.
Further, the concrete mode of the monocycle comparison are as follows: take N number of different time points within the monocycle, be greater than door
The time point of limit value, upper voltage value was identical, then thought that signal is identical in the period.
Using the test method of local voice mould set product acoustical behavior of the present invention, can fast and accurately judge
Whether the acoustical behavior of voice mould group is qualified up to standard, reduces the step process of mould group test, accelerates the time of mould group test,
Mould group testing efficiency is improved, the testing cost of mould group is reduced, the equipment test in the identification of all native languages can be applied
In method, play a role in promoting to popularizing for voice artificial intelligence.
Detailed description of the invention
Fig. 1 is a kind of exemplary embodiment flow chart of the present invention；
Fig. 2 is the schematic diagram that each waveform signal of the present invention compares；Abscissa is the time in Fig. 2, and ordinate is voltage.
Specific embodiment
Specific embodiments of the present invention will be described in further detail with reference to the accompanying drawing.
The test method of local voice mould set product acoustical behavior of the present invention, includes the following steps:
S1；Benchmark digital signal A1 is converted by fixed algorithm by analog audio signal A0；The fixed algorithm is voice mould
Analytical algorithm of the group to analog audio signal；
S2；Analog audio signal A0 is inputted into voice mould group to be measured, analog audio signal is converted comparison by voice mould group to be measured
Digital signal A2；
S3；Benchmark digital signal A1 is compared with digital signal A2 is compared, judge if the two similarity reaches standard to
The acoustical behavior for surveying voice mould group is up to standard, otherwise not up to standard.
A more typical analog audio signal A0 is provided as shown in Figure 2, A0 is sine wave signal, is by fixed algorithm
After the signal method for transformation that the normal voice mould group of performance is carried out, benchmark digital signal A1 is obtained, benchmark digital signal A1
Waveform in Fig. 2 only to illustrate for the purpose of, obtained benchmark digital signal A1 can store voice main control chip or and its
In the storage equipment of connection.
Analog audio signal A0 can be the constant periodic voltage signal of fixed frequency response i.e. frequency amplitude, each period
All the same and voltage magnitude is identical, facilitates in measurement and compares, but analog audio signal A0 can also be with frequency response unfixed non-week
Phase property waveform.
As shown in Figure 2, benchmark digital signal is usually square.The canonical form of digital audio and video signals is IIS
(Inter-IC Sound) or I2S standard signal are PHILIPS Co.s for digital audio-frequency apparatus, such as CD Player, digital audio
A kind of bus standard imitating the audio data transmission between processor, DTV sound system and formulating.
After the acquisition and storage for completing benchmark digital signal A1, it can start to test mould group to be measured.
When being tested, analog audio signal A0 can be issued by exterior terminals such as PC, be sent to by Audio Data Line
The simulation input pin of die trial group sound intermediate frequency decoding chip to be measured, audio decoder chip to the audio signal carry out digital-to-analogue conversion and
IIS encoding and decoding obtain comparing digital signal A2.
In the step S2, the clock frequency that audio decoder chip is converted to iis can be 1Mhz, and left and right alignment clock can
Think 16Khz.The input clock of audio decoder chip is generally provided by voice main control chip, IIS clock and left and right alignment clock
And provided by voice main control chip, the comparison digital signal A2 after conversion, which is then exported by audio decoder chip, gives voice master control core
Piece.
The left and right alignment clock respectively includes left-justify clock and Right Aligns clock, left-justify (left-
Justified), i.e. the clock signal that is aligned to byte position on the left of data of clock edge, Right Aligns (right-justified),
That is clock signal of the clock edge to byte position alignment on the right side of data.
Pre-stored benchmark digital signal A1 is compared voice main control chip with digital signal A2 is compared.
The mode of comparison can be compared using Cycle by Cycle, such as a segment of audio signal one shares 100 clock cycle, to every
One period compared respectively in chronological order, and the ratio of complete signal clock cycle number is accounted for according to the same period quantity detected
Judge whether up to standard.It is described up to standard are as follows: for example established standards are 97% or more up to standard, then in 100 clock cycle, have 97 with
On clock cycle signal it is identical, then it is assumed that it is up to standard, judge acoustic model qualification.
For the monocycle comparison concrete mode can use voltage sample, specifically: taken within the monocycle it is N number of not
Same time point, as shown in Fig. 2, various time points can uniformly be chosen, it can also be with random distribution, such as 100 time points are selected,
Threshold value 95 is set, if 95 or more point voltage values are identical in the monocycle, then it is assumed that the period is same period, such as is schemed
In 2, cycle T 1 and T3 voltage value on substantial portion of time point is different, it may be determined that be different, each point voltage in cycle T 2
It is then substantially identical everywhere.
Using the test method of local voice mould set product acoustical behavior of the present invention, can fast and accurately judge
Whether the acoustical behavior of voice mould group is qualified up to standard, reduces the step process of mould group test, accelerates the time of mould group test,
Mould group testing efficiency is improved, the testing cost of mould group is reduced, the equipment test in the identification of all native languages can be applied
In method, play a role in promoting to popularizing for voice artificial intelligence.
Previously described is each preferred embodiment of the invention, if the preferred embodiment in each preferred embodiment
It is not obvious contradictory or premised on a certain preferred embodiment, each preferred embodiment can any stack combinations
Use, the design parameter in the embodiment and embodiment only for the purpose of clearly stating the inventor's invention verification process, and
It is non-to limit scope of patent protection of the invention, scope of patent protection of the invention is still subject to the claims, all
It is that similarly should be included within the scope of the present invention with the variation of equivalent structure made by description of the invention.
Claims (7)
1. a kind of test method of local voice mould set product acoustical behavior, which comprises the steps of:
S1；Benchmark digital signal A1 is converted by fixed algorithm by analog audio signal A0；The fixed algorithm is voice mould
Analytical algorithm of the group to analog audio signal；
S2；Analog audio signal A0 is inputted into voice mould group to be measured, analog audio signal is converted comparison by voice mould group to be measured
Digital signal A2；
S3；Benchmark digital signal A1 is compared with digital signal A2 is compared, judge if the two similarity reaches standard to
The acoustical behavior for surveying voice mould group is up to standard, otherwise not up to standard.
2. the test method of local voice mould set product acoustical behavior as described in claim 1, which is characterized in that the benchmark
Digital signal A1 and to compare digital signal A2 be standard iis digital signal.
3. the test method of local voice mould set product acoustical behavior as claimed in claim 2, which is characterized in that be converted to mark
The clock frequency of quasi- iis digital signal is 1Mhz；Left and right alignment clock is 16Khz.
4. the test method of local voice mould set product acoustical behavior as described in claim 1, which is characterized in that the simulation
Audio signal A0 is fixed frequency response curve.
5. the test method of local voice mould set product acoustical behavior as claimed in claim 4, it is characterised in that: the simulation
Audio signal A0 is frequency 1k hertz, the sine wave of amplitude 1V.
6. the test method of local voice mould set product acoustical behavior as described in claim 1, which is characterized in that the step
Way of contrast in S3 is the monocycle comparison that the clock cycle one by one is chronologically carried out to signal, according to the same period detected
The ratio that quantity accounts for complete signal clock cycle number judges whether up to standard.
7. the test method of local voice mould set product acoustical behavior as claimed in claim 6, which is characterized in that the single-revolution
The concrete mode of phase comparison are as follows: N number of different time points are taken within the monocycle, it is identical greater than the time point of threshold value upper voltage value,
Then think that signal is identical in the period.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910358064.1A CN109979434A (en) | 2019-04-30 | 2019-04-30 | The test method of local voice mould set product acoustical behavior |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910358064.1A CN109979434A (en) | 2019-04-30 | 2019-04-30 | The test method of local voice mould set product acoustical behavior |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109979434A true CN109979434A (en) | 2019-07-05 |
Family
ID=67087175
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910358064.1A Pending CN109979434A (en) | 2019-04-30 | 2019-04-30 | The test method of local voice mould set product acoustical behavior |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109979434A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112233654A (en) * | 2019-07-15 | 2021-01-15 | 成都启英泰伦科技有限公司 | System and method for detecting recognition rate of local off-line intelligent voice recognition module |
| CN112417109A (en) * | 2020-10-26 | 2021-02-26 | 出门问问(苏州)信息科技有限公司 | Method and device for testing man-machine conversation system |
| CN113094223A (en) * | 2021-04-14 | 2021-07-09 | 成都启英泰伦科技有限公司 | Method for detecting voice recognition module audio channel hardware function |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102368384A (en) * | 2011-10-19 | 2012-03-07 | 福建联迪商用设备有限公司 | Voice module test method and voice module test device |
| CN104050964A (en) * | 2014-06-17 | 2014-09-17 | 公安部第三研究所 | Audio signal reduction degree detecting method and system |
| CN104834393A (en) * | 2015-06-04 | 2015-08-12 | 携程计算机技术（上海）有限公司 | Automatic testing device and system |
| CN104952444A (en) * | 2015-04-27 | 2015-09-30 | 桂林电子科技大学 | Chinese oral English quality assessment method independent from text |
| US20160352892A1 (en) * | 2014-11-12 | 2016-12-01 | 24/7 Customer, Inc. | Method and apparatus for facilitating speech application testing |
| CN108091348A (en) * | 2018-01-31 | 2018-05-29 | 佛山博智医疗科技有限公司 | Speech audiometry response identification test device and method |
-
2019
- 2019-04-30 CN CN201910358064.1A patent/CN109979434A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102368384A (en) * | 2011-10-19 | 2012-03-07 | 福建联迪商用设备有限公司 | Voice module test method and voice module test device |
| CN104050964A (en) * | 2014-06-17 | 2014-09-17 | 公安部第三研究所 | Audio signal reduction degree detecting method and system |
| US20160352892A1 (en) * | 2014-11-12 | 2016-12-01 | 24/7 Customer, Inc. | Method and apparatus for facilitating speech application testing |
| CN104952444A (en) * | 2015-04-27 | 2015-09-30 | 桂林电子科技大学 | Chinese oral English quality assessment method independent from text |
| CN104834393A (en) * | 2015-06-04 | 2015-08-12 | 携程计算机技术（上海）有限公司 | Automatic testing device and system |
| CN108091348A (en) * | 2018-01-31 | 2018-05-29 | 佛山博智医疗科技有限公司 | Speech audiometry response identification test device and method |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112233654A (en) * | 2019-07-15 | 2021-01-15 | 成都启英泰伦科技有限公司 | System and method for detecting recognition rate of local off-line intelligent voice recognition module |
| CN112417109A (en) * | 2020-10-26 | 2021-02-26 | 出门问问(苏州)信息科技有限公司 | Method and device for testing man-machine conversation system |
| CN112417109B (en) * | 2020-10-26 | 2023-08-01 | 问问智能信息科技有限公司 | Method and device for testing man-machine dialogue system |
| CN113094223A (en) * | 2021-04-14 | 2021-07-09 | 成都启英泰伦科技有限公司 | Method for detecting voice recognition module audio channel hardware function |
| CN113094223B (en) * | 2021-04-14 | 2023-05-02 | 成都启英泰伦科技有限公司 | Method for detecting hardware function of voice recognition module audio channel |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109087669B (en) | Audio similarity detection method and device, storage medium and computer equipment | |
| CN109979434A (en) | The test method of local voice mould set product acoustical behavior | |
| CN105244026B (en) | A kind of method of speech processing and device | |
| CN102930866B (en) | Evaluation method for student reading assignment for oral practice | |
| CN107147618A (en) | A kind of user registering method, device and electronic equipment | |
| CN107423809A (en) | The multi-modal exchange method of virtual robot and system applied to net cast platform | |
| CN104575504A (en) | Method for personalized television voice wake-up by voiceprint and voice identification | |
| CN108847215B (en) | Method and device for voice synthesis based on user timbre | |
| CN109256115A (en) | A kind of speech detection system and method for intelligent appliance | |
| CN109326305B (en) | Method and system for batch testing of speech recognition and text synthesis | |
| CN108962283A (en) | A kind of question terminates the determination method, apparatus and electronic equipment of mute time | |
| CN108766441A (en) | A kind of sound control method and device based on offline Application on Voiceprint Recognition and speech recognition | |
| CN109949808A (en) | The speech recognition appliance control system and method for compatible mandarin and dialect | |
| CN109767763B (en) | Method and device for determining user-defined awakening words | |
| CN110782875B (en) | Voice rhythm processing method and device based on artificial intelligence | |
| CN110782896A (en) | Measuring instrument testing system and method based on voice control | |
| CN109637536B (en) | Method and device for automatically identifying semantic accuracy | |
| CN111724781B (en) | Audio data storage method, device, terminal and storage medium | |
| CN209328511U (en) | A kind of portable AI interactive voice control system | |
| CN111933149A (en) | Voice interaction method, wearable device, terminal and voice interaction system | |
| CN111724769A (en) | Production method of intelligent household voice recognition model | |
| CN112634897B (en) | Equipment awakening method and device, storage medium and electronic device | |
| CN109377993A (en) | Intelligent voice system and its voice awakening method and intelligent sound equipment | |
| CN111968646A (en) | Voice recognition method and device | |
| CN113595811B (en) | Equipment performance testing method and device, storage medium and electronic device |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190705 |
|
| WD01 | Invention patent application deemed withdrawn after publication |