CN105469656A - Spoken language learning system and operating method of the system - Google Patents
Spoken language learning system and operating method of the system Download PDFInfo
- Publication number
- CN105469656A CN105469656A CN201510821973.6A CN201510821973A CN105469656A CN 105469656 A CN105469656 A CN 105469656A CN 201510821973 A CN201510821973 A CN 201510821973A CN 105469656 A CN105469656 A CN 105469656A
- Authority
- CN
- China
- Prior art keywords
- module
- voice
- audio
- recording
- learning system
- 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
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B5/00—Electrically-operated educational appliances
- G09B5/04—Electrically-operated educational appliances with audible presentation of the material to be studied
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention relates to a spoken language learning system. The system comprises an audio decoding module used for audio file decoding, a voice breakpoint searching module used for automatically calculating and searching a voice breakpoint in an audio, an audio playing module used for carrying out playing and playback on audio data, an adaptive recording module used for adaptively recording a user voice and a record playback module used for carrying out playback on a record. The audio decoding module is connected to the voice breakpoint searching module. And the voice breakpoint searching module is connected to the audio playing module. By using the spoken language learning system, a problem of simultaneously and interactively training listening and speaking capabilities during English learning is effectively solved.
Description
Technical field
The present invention relates to a kind of verbal learning system, and the How It Works of this system.
Background technology
The Learning demands of Oral English Practice, by the training of listening and speaking repeatedly, just can improve learning efficiency.And people, for the English audio file bought or download, are generally use unidirectional audio player at present, user can only train the ability of oneself listening, the ability that can not oneself is trained timely to say.
In view of this, necessaryly provide a kind of system that user can be allowed to utilize conventional audio file or network audio to realize the combined training listened, say, confirm, to improve learning efficiency.
Summary of the invention
A kind of verbal learning system that the present invention provides to solve the problem, comprise: for the audio decoder module of audio file decoding, for automatically calculating the voice interruption point search module finding voice breakpoint in audio frequency, for playing the audio playing module with plays back audio data, for recording the self-adaptation recording module of the voice of user adaptively, and for playback recording recording playback module, described audio decoder module and described voice interruption point search model calling, described voice interruption point search module is connected with described audio playing module.
Preferably, described audio decoder module supports the decoding of the audio files such as MP3 or MVA or online audio stream.
Preferably, the decoded data of random length is read in the support of described audio decoder module at every turn.
Preferably, described self-adaptation recording module has the noise reduction module of support voice noise reduction process.
Preferably, voice are saved in a recording file MicFile by described self-adaptation recording module, and described recording playback module can trigger described recording file MicFile automatically.
The present invention also provides a kind of How It Works of upper predicate learning system, and described How It Works comprises:
Step 1, audio decoder module are decoded to audio file;
Step 2, voice interruption point search module calculate the voice interruption point found in audio frequency automatically;
Step 3, audio playing module are play and plays back audio data;
Step 4, self-adaptation recording module record the voice of user adaptively;
The recording of step 5, recording playback module replaying user.
Preferably, in described step 2, described voice interruption point search module is based on whole voice data buffer memory or automatically calculate the voice interruption point found inside decoded data stream based on partial data stream.
Preferably, in described step 2, described voice interruption point search module uses energy threshold voice breaking point detection algorithm.
Preferably, in described step 4, if continue not occur efficient voice in physique very first time length T1, then automatically terminate to record; If there is efficient voice in very first time length T1, then enter quiet section of judgement, if continue a second time span T2 to occur quiet section, then automatically terminate to record.
Preferably, after described step 5, further comprising the steps of:
Step 6, described audio decoder module and voice interruption point search module carry out follow-up data decode and breaking point detection.
Beneficial effect of the present invention is: this verbal learning system efficiently solves the problem of the ability of interactive training listening and speaking simultaneously in English study.As long as just can realize the circuit training sentence by sentence of listening to, repeating, confirming based on common audio file or network audio stream, support simple sentence repeat playing function in addition, spoken learning efficiency can be significantly improved.
Accompanying drawing explanation
The learning system block schematic illustration that Fig. 1 provides for the embodiment of the present invention.
Embodiment
Below in conjunction with accompanying drawing, the present invention is further elaborated:
The invention provides a kind of verbal learning system.The input object of this verbal learning system is audio file, and wherein mainly voice are main, do not comprise lasting background music.
As shown in Figure 1, this verbal learning system comprises audio decoder module, for the decoding of audio file; Voice interruption point search module, for automatically calculating the voice interruption point found in audio frequency; Audio playing module, for playing and plays back audio data; Self-adaptation recording module, for recording the voice of user adaptively; Recording playback module, for the recording of replaying user.
Audio decoder module and voice interruption point search model calling, transfer to voice interruption point search module by decoded decoded data stream.Voice interruption point search module is connected with audio playing module, and the data of sound bite are passed to audio playing module.
The present invention also provides the How It Works of above-mentioned verbal learning system, comprises the following steps:
Step 1, audio decoder module are decoded to audio file;
Step 2, voice interruption point search module calculate the voice interruption point found in audio frequency automatically;
Step 3, audio playing module are play and plays back audio data;
Step 4, self-adaptation recording module record the voice of user adaptively;
The recording of step 5, recording playback module replaying user.
Audio decoder module supports the decoding process of the audio files such as MP3 or MVA, also supports the decoding of online audio stream, and supports each decoded data reading random length.For different platforms, suitable cache size can be selected, each decoded data PcmData reading appropriate length.
Voice interruption point search module can based on whole voice data buffer memory, also can automatically calculate based on partial data stream the voice interruption point found inside decoded data stream, use algorithm to include but not limited to the energy threshold voice breaking point detection scheduling algorithm commonly used.As: based on the decoded data PcmData obtained, in units of 20ms or 40ms frame, carry out the calculating of speech energy and zero-crossing rate above, then by sliding window and threshold judgement, judge whether to there is voice interruption point.If there is voice interruption point, then record breakpoint information, and start recording module after audio playing module plays sound bite.If there is no voice interruption point, then directly pass to audio playing module data and play voice.
Voice playing module is play-overed after receiving data above, if do not have data, automatically stops playing.Voice playing module can play the sound bite data that voice interruption point search module above exports; Also can certain sound bite of specifying of repeat playing.
Self-adaptation recording module adaptive control record length length can save as audio file user speech input recording, and self-adaptation recording module has noise reduction module, support voice noise reduction process simultaneously.Wherein the algorithm of adaptive control duration includes but not limited to the quiet segment length control of speech terminals detection, self-adaptation etc.After self-adaptation recording module receives enabled instruction, start recording process, the data MicData that self-adaptation recording module buffer memory microphone apparatus exports, be saved in a recording file MicFile, breaking point detection carried out to data MicData simultaneously.If continue not occur efficient voice in very first time length T1, automatically terminate to record.If there is efficient voice in very first time length T1, then enter quiet section of judgement, if continue the second time span T2 to occur quiet section, then automatically terminate to record.After recording receives, automatically start recording playback module.
Recording playback module can trigger the recording file MicFile playing user automatically, confirms the oneself oneself repeating voice for user.Start playback file MicFile after recording playback module receives instruction, after finishing, comprise the following steps: notification audio decoder module and voice interruption point search module carry out follow-up data decode and breaking point detection.
If period user input instruction, then notification audio decoder module decoded data from the point of interruption position of preserving above.
This verbal learning system efficiently solves the problem of the ability of interactive training listening and speaking simultaneously in English study.As long as just can realize the circuit training sentence by sentence of listening to, repeating, confirming based on common audio file or network audio stream, support simple sentence repeat playing function in addition, spoken learning efficiency can be significantly improved.
The above embodiment, just preferred embodiments of the present invention, be not limit practical range of the present invention, therefore all equivalences done according to structure, feature and the principle described in the present patent application the scope of the claims change or modify, and all should be included in patent claim of the present invention.
Claims (10)
1. a verbal learning system, it is characterized in that, described verbal learning system comprises: for the audio decoder module of audio file decoding, for automatically calculating the voice interruption point search module finding voice breakpoint in audio frequency, for playing the audio playing module with plays back audio data, for recording the self-adaptation recording module of the voice of user adaptively, and for playback recording recording playback module
Described audio decoder module and described voice interruption point search model calling, described voice interruption point search module is connected with described audio playing module.
2. verbal learning system as claimed in claim 1, is characterized in that, described audio decoder module supports the decoding of the audio files such as MP3 or MVA or online audio stream.
3. verbal learning system as claimed in claim 1, it is characterized in that, the decoded data of random length is read in the support of described audio decoder module at every turn.
4. the verbal learning system as described in claim 1 or 2 or 3, it is characterized in that, described self-adaptation recording module has the noise reduction module of support voice noise reduction process.
5. verbal learning system as claimed in claim 4, it is characterized in that, voice are saved in a recording file MicFile by described self-adaptation recording module, and described recording playback module can trigger described recording file MicFile automatically.
6. a How It Works for the arbitrary verbal learning system as described in claim 1-5, it is characterized in that, described How It Works comprises:
Step 1, audio decoder module are decoded to audio file;
Step 2, voice interruption point search module calculate the voice interruption point found in audio frequency automatically;
Step 3, audio playing module are play and plays back audio data;
Step 4, self-adaptation recording module record the voice of user adaptively;
The recording of step 5, recording playback module replaying user.
7. How It Works as claimed in claim 6, is characterized in that, in described step 2, described voice interruption point search module is based on whole voice data buffer memory or automatically calculate the voice interruption point found inside decoded data stream based on partial data stream.
8. How It Works as claimed in claim 6, is characterized in that, in described step 2, described voice interruption point search module uses energy threshold voice breaking point detection algorithm.
9. How It Works as claimed in claim 6, is characterized in that, in described step 4, if continue not occur efficient voice in physique very first time length T1, then automatically terminates to record; If there is efficient voice in very first time length T1, then enter quiet section of judgement, if continue a second time span T2 to occur quiet section, then automatically terminate to record.
10. How It Works as claimed in claim 6, is characterized in that, after described step 5, further comprising the steps of:
Step 6, described audio decoder module and voice interruption point search module carry out follow-up data decode and breaking point detection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510821973.6A CN105469656A (en) | 2015-11-23 | 2015-11-23 | Spoken language learning system and operating method of the system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510821973.6A CN105469656A (en) | 2015-11-23 | 2015-11-23 | Spoken language learning system and operating method of the system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105469656A true CN105469656A (en) | 2016-04-06 |
Family
ID=55607296
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510821973.6A Pending CN105469656A (en) | 2015-11-23 | 2015-11-23 | Spoken language learning system and operating method of the system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105469656A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2333049Y (en) * | 1998-06-09 | 1999-08-11 | 刘兆有 | Intelligence foreign language learning machine |
| KR100470736B1 (en) * | 2002-08-08 | 2005-03-10 | 인벤텍 코오포레이션 | Language listening and speaking training system and method with random test, appropriate shadowing and instant paraphrase functions |
| CN1624685A (en) * | 2003-12-02 | 2005-06-08 | 英业达股份有限公司 | Paragraph type language learning system and its method |
| CN1787070A (en) * | 2005-12-09 | 2006-06-14 | 北京凌声芯语音科技有限公司 | Chip upper system for language learner |
| KR20070092604A (en) * | 2006-03-10 | 2007-09-13 | 김태훈 | Method for listening,speaking and writing through memory increase of english voice |
| CN201465325U (en) * | 2009-05-11 | 2010-05-12 | 刘正江 | Multi-mode automatic integral-semantic sentence identification learning machine |
| KR20100072627A (en) * | 2008-12-22 | 2010-07-01 | 심명은 | Language teaching method for adjusting height of voice |
| JP2011085641A (en) * | 2009-10-13 | 2011-04-28 | Power Shift Inc | Language learning support system and language learning support method |
| CN103413550A (en) * | 2013-08-30 | 2013-11-27 | 苏州跨界软件科技有限公司 | Man-machine interactive language learning system and method |
| CN105006179A (en) * | 2015-05-29 | 2015-10-28 | 广东小天才科技有限公司 | Method and apparatus for repeating content of voice input |
-
2015
- 2015-11-23 CN CN201510821973.6A patent/CN105469656A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2333049Y (en) * | 1998-06-09 | 1999-08-11 | 刘兆有 | Intelligence foreign language learning machine |
| KR100470736B1 (en) * | 2002-08-08 | 2005-03-10 | 인벤텍 코오포레이션 | Language listening and speaking training system and method with random test, appropriate shadowing and instant paraphrase functions |
| CN1624685A (en) * | 2003-12-02 | 2005-06-08 | 英业达股份有限公司 | Paragraph type language learning system and its method |
| CN1787070A (en) * | 2005-12-09 | 2006-06-14 | 北京凌声芯语音科技有限公司 | Chip upper system for language learner |
| KR20070092604A (en) * | 2006-03-10 | 2007-09-13 | 김태훈 | Method for listening,speaking and writing through memory increase of english voice |
| KR20100072627A (en) * | 2008-12-22 | 2010-07-01 | 심명은 | Language teaching method for adjusting height of voice |
| CN201465325U (en) * | 2009-05-11 | 2010-05-12 | 刘正江 | Multi-mode automatic integral-semantic sentence identification learning machine |
| JP2011085641A (en) * | 2009-10-13 | 2011-04-28 | Power Shift Inc | Language learning support system and language learning support method |
| CN103413550A (en) * | 2013-08-30 | 2013-11-27 | 苏州跨界软件科技有限公司 | Man-machine interactive language learning system and method |
| CN105006179A (en) * | 2015-05-29 | 2015-10-28 | 广东小天才科技有限公司 | Method and apparatus for repeating content of voice input |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105304080B (en) | Speech synthetic device and method | |
| Barker et al. | The third ‘CHiME’speech separation and recognition challenge: Dataset, task and baselines | |
| CN104464723B (en) | A kind of voice interactive method and system | |
| Li et al. | Semi-supervised training for end-to-end models via weak distillation | |
| CN104205215B (en) | Automatic real-time verbal therapy | |
| CN110148402A (en) | Method of speech processing, device, computer equipment and storage medium | |
| JP2019211749A (en) | Method and apparatus for detecting starting point and finishing point of speech, computer facility, and program | |
| Hwang et al. | TTS-by-TTS: TTS-driven data augmentation for fast and high-quality speech synthesis | |
| CN109979474B (en) | Voice equipment and user speech rate correction method and device thereof and storage medium | |
| US20090271197A1 (en) | Identifying features in a portion of a signal representing speech | |
| WO2017006766A1 (en) | Voice interaction method and voice interaction device | |
| CN106297790A (en) | The voiceprint service system of robot and service control method thereof | |
| WO2016165334A1 (en) | Voice processing method and apparatus, and terminal device | |
| CN105551512A (en) | Audio format conversion method and apparatus | |
| CN112382310B (en) | Human voice audio recording method and device | |
| US20210118464A1 (en) | Method and apparatus for emotion recognition from speech | |
| JP2017021125A5 (en) | Voice dialogue apparatus and voice dialogue method | |
| WO2014118420A1 (en) | Method and system for obtaining relevant information from a voice communication | |
| CN111739536A (en) | Audio processing method and device | |
| WO2016027909A1 (en) | Data structure, interactive voice response device, and electronic device | |
| CN109616127A (en) | A kind of audio data fusion method | |
| CN105469656A (en) | Spoken language learning system and operating method of the system | |
| WO2023116243A1 (en) | Data conversion method and computer storage medium | |
| JP5223843B2 (en) | Information processing apparatus and program | |
| Xu et al. | The TAL System for the INTERSPEECH2021 Shared Task on Automatic Speech Recognition for Non-Native Childrens Speech. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160406 |