CN107729321A - A kind of method for correcting error of voice identification result - Google Patents
A kind of method for correcting error of voice identification result Download PDFInfo
- Publication number
- CN107729321A CN107729321A CN201710994082.XA CN201710994082A CN107729321A CN 107729321 A CN107729321 A CN 107729321A CN 201710994082 A CN201710994082 A CN 201710994082A CN 107729321 A CN107729321 A CN 107729321A
- Authority
- CN
- China
- Prior art keywords
- text
- identification result
- voice identification
- candidate
- phonetic
- 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
- 238000000034 method Methods 0.000 title claims abstract description 10
- 230000002452 interceptive effect Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 240000005373 Panax quinquefolius Species 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 235000011225 shan shi Nutrition 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/253—Grammatical analysis; Style critique
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/232—Orthographic correction, e.g. spell checking or vowelisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Acoustics & Sound (AREA)
- Human Computer Interaction (AREA)
- Machine Translation (AREA)
Abstract
A kind of method for correcting error of voice identification result, including voice identification result is pre-processed；The words and phrases easily to be malfunctioned in voice identification result are found out, or important word to be corrected, word are parsed to text semantic；Treat and correct word, word progress phonetic notation, including two kinds of phonetic modes of spelling and each first letter of pinyin, obtain phonetic corresponding to voice identification result to be corrected, corresponding phonetic refers to no tone；According to the phonetic spelling mode, using the true algorithm of editing distance, best candidate text and suboptimum candidate's text are determined；According to the first letter of pinyin, using editing distance algorithm, best candidate text and suboptimum candidate's text are determined；All best candidate texts and suboptimum candidate text are merged, the candidate item repeated only retains one；Quasi- candidate's text is replaced respectively and treats corrected text, calculates the respective sentence probability after each replacement respectively using n grama language models, chooses probability highest as the final voice identification result to be corrected.
Description
Technical field
The invention belongs to field of artificial intelligence, more particularly to a kind of method for correcting error of voice identification result.
Background technology
Ripe day by day with speech recognition technology, interactive voice use range is more and more wider.Compared to other interactive modes,
The interactive mode that interactive voice is realized more meets the daily habits of people, also highly efficient.At present, interactive voice mode is in intelligence
Energy household, Industry Control, the every field such as auxiliary are driven, be obtained for extensive use.
In actual applications, due to the influence of the factors such as ambient noise, dialect, the knot of speech recognition during interactive voice
Fruit is often inconsistent with the expression of user.Especially under everyday spoken english scene, the error rate of speech recognition is higher.And prior art
In, all concentrate on lifting speech recognition accuracy, but lack the approach of error correction to identification mistake, thus have impact on speech recognition
The further genralrlization of technology.
The content of the invention
The present invention provides a kind of method for correcting error of voice identification result, accurate to be carried out to the resulting text of speech recognition
Error correction.
A kind of method for correcting error of voice identification result, comprises the following steps：
S11, voice identification result is pre-processed；
S12, finds out the words and phrases easily to be malfunctioned in voice identification result, or text semantic is parsed important word to be corrected,
Word；
S13, treat and correct word, word progress phonetic notation, including two kinds of phonetic modes of spelling and each first letter of pinyin, obtain waiting to entangle
Phonetic corresponding to positive voice identification result, corresponding phonetic refer to no tone；
S14, according to the phonetic spelling mode, using the true algorithm of editing distance, determine that best candidate text and suboptimum are waited
Selection sheet；
S15, according to the first letter of pinyin, editing distance algorithm is reused, determine that best candidate text and suboptimum are waited
Selection sheet；
S16, all best candidate texts and suboptimum candidate text are merged, the candidate item repeated only retains one；
S17, quasi- candidate's text is replaced treat corrected text respectively, calculated using n-grama language models and respectively replaced respectively
Respective sentence probability after changing, probability highest is chosen as the final voice identification result to be corrected.
Pretreatment in step S11 includes participle, part-of-speech tagging, removes stop words and carries out syntactic analysis text maninulation.
The present invention by being segmented to voice identification result, part-of-speech tagging, remove stop words and carry out syntactic analysis.Will
As a result middle V-O construction phrase, verb, noun and the word conduct text to be corrected not occurred in dictionary, while pay attention to keeping
Order of each word in former speech text；Text results to be corrected are segmented, and obtain the phonetic corresponding to each participle；Root
Candidate word is obtained from dictionary according to each participle phonetic, and best candidate word is determined in candidate word；Judge described optimal
Whether candidate word meets preparatory condition；If meeting preparatory condition, original text word to be corrected is replaced with the best candidate word.Will
All correction results merge, and show that result is corrected in final speech recognition.
Brief description of the drawings
Detailed description below, above-mentioned and other mesh of exemplary embodiment of the invention are read by reference to accompanying drawing
, feature and advantage will become prone to understand.In the accompanying drawings, if showing the present invention's by way of example, and not by way of limitation
Dry embodiment, wherein：
The schematic flow sheet of method for correcting error of voice identification result in Fig. 1 embodiment of the present invention.
Embodiment
Referring to Fig. 1, the method for the present embodiment includes:
S11:Voice identification result is segmented, part-of-speech tagging, stop words is removed and carries out the text maninulation such as syntactic analysis
S12:According to technology that is existing or occurring in the future, find out easily error or text semantic is parsed and important wait to correct
Word, word.Especially pay attention to V-O construction phrase, verb, noun and the word not occurred in dictionary in voice identification result.
S13:Treat and correct word, word progress phonetic notation, obtain phonetic corresponding to voice identification result to be corrected, corresponding phonetic
Refer to no tone.
Such a situation divides a variety of situations again, is elaborated as follows：
Unisonance malapropism, takes spelling：
For example, voice identification result to be corrected is " seeing that three sound three are ", corresponding phonetic is after having divided word:kan san
sheng san shi
Pronounce nonstandard, take each prefix letter：
For example, voice identification result to be corrected is " seeing that Shan Shan mountains are ", corresponding phonetic is after having divided word:kan shan
Shan shan shi, each initial letter k s s s s can be taken to it
S14:First according to the phonetic spelling, using the true algorithm of editing distance, determine that best candidate text and suboptimum are waited
Selection sheet；
S15：Secondly according to the first letter of pinyin, editing distance algorithm is reused, determines best candidate text and secondary
Excellent candidate's text.
S16：All best candidate texts and suboptimum candidate text are merged, the candidate item repeated only retains one, owns
It is referred to as the candidate's text that is defined.
S17:Quasi- candidate's text is replaced respectively and treats corrected text, is calculated using n-grama language models and respectively replaced respectively
Respective sentence probability after changing, probability highest is chosen as the final voice identification result to be corrected
What deserves to be explained is although foregoing teachings describe the essence of the invention by reference to some embodiments
God and principle, it should be appreciated that, the present invention is not limited to disclosed embodiment, the also unawareness of the division to each side
The feature that taste in these aspects can not combine, and this division is merely to the convenience of statement.It is contemplated that cover appended power
Included various modifications and equivalent arrangements in the spirit and scope that profit requires.
Claims (2)
1. a kind of method for correcting error of voice identification result, it is characterised in that comprise the following steps：
S11, voice identification result is pre-processed；
S12, the words and phrases easily to be malfunctioned in voice identification result are found out, or important word to be corrected, word are parsed to text semantic；
S13, treat and correct word, word progress phonetic notation, including two kinds of phonetic modes of spelling and each first letter of pinyin, obtain language to be corrected
Phonetic corresponding to sound recognition result, corresponding phonetic refer to no tone；
S14, according to the phonetic spelling mode, using the true algorithm of editing distance, determine best candidate text and suboptimum candidate text
This；
S15, according to the first letter of pinyin, editing distance algorithm is reused, determine best candidate text and suboptimum candidate text
This；
S16, all best candidate texts and suboptimum candidate text are merged, the candidate item repeated only retains one；
S17, quasi- candidate's text is replaced treat corrected text respectively, after calculating each replacement respectively using n-grama language models
Respective sentence probability, choose probability highest as voice identification result to be corrected described in final.
2. method for correcting error of voice identification result as claimed in claim 1, it is characterised in that the pretreatment in step S11 includes
Participle, part-of-speech tagging, remove stop words and carry out syntactic analysis text maninulation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710994082.XA CN107729321A (en) | 2017-10-23 | 2017-10-23 | A kind of method for correcting error of voice identification result |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710994082.XA CN107729321A (en) | 2017-10-23 | 2017-10-23 | A kind of method for correcting error of voice identification result |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107729321A true CN107729321A (en) | 2018-02-23 |
Family
ID=61212500
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710994082.XA Pending CN107729321A (en) | 2017-10-23 | 2017-10-23 | A kind of method for correcting error of voice identification result |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107729321A (en) |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108595419A (en) * | 2018-04-11 | 2018-09-28 | 广州视源电子科技股份有限公司 | Candidate word evaluation method, candidate word sorting method and device |
| CN108595431A (en) * | 2018-04-28 | 2018-09-28 | 海信集团有限公司 | Interactive voice text error correction method, device, terminal and storage medium |
| CN108694166A (en) * | 2018-04-11 | 2018-10-23 | 广州视源电子科技股份有限公司 | Candidate word evaluation method and device, computer equipment and storage medium |
| CN108804414A (en) * | 2018-05-04 | 2018-11-13 | 科沃斯商用机器人有限公司 | Text modification method, device, smart machine and readable storage medium storing program for executing |
| CN108959250A (en) * | 2018-06-27 | 2018-12-07 | 众安信息技术服务有限公司 | A kind of error correction method and its system based on language model and word feature |
| CN109522550A (en) * | 2018-11-08 | 2019-03-26 | 和美（深圳）信息技术股份有限公司 | Text information error correction method, device, computer equipment and storage medium |
| CN109684643A (en) * | 2018-12-26 | 2019-04-26 | 湖北亿咖通科技有限公司 | Text recognition method, electronic equipment and computer-readable medium based on sentence vector |
| CN109710929A (en) * | 2018-12-18 | 2019-05-03 | 金蝶软件（中国）有限公司 | A kind of bearing calibration, device, computer equipment and the storage medium of speech recognition text |
| CN109918485A (en) * | 2019-01-07 | 2019-06-21 | 口碑(上海)信息技术有限公司 | The method and device of speech recognition vegetable, storage medium, electronic device |
| CN109977412A (en) * | 2019-03-29 | 2019-07-05 | 北京林业大学 | A kind of field value error correction method, device, readable medium and storage control |
| CN110176237A (en) * | 2019-07-09 | 2019-08-27 | 北京金山数字娱乐科技有限公司 | A kind of audio recognition method and device |
| CN110210029A (en) * | 2019-05-30 | 2019-09-06 | 浙江远传信息技术股份有限公司 | Speech text error correction method, system, equipment and medium based on vertical field |
| CN110265019A (en) * | 2019-07-03 | 2019-09-20 | 中通智新(武汉)技术研发有限公司 | A kind of method and speech robot people's system of speech recognition |
| CN110600005A (en) * | 2018-06-13 | 2019-12-20 | 蔚来汽车有限公司 | Speech recognition error correction method and apparatus, computer device and recording medium |
| CN110765763A (en) * | 2019-09-24 | 2020-02-07 | 金蝶软件（中国）有限公司 | Error correction method and device for speech recognition text, computer equipment and storage medium |
| CN111274785A (en) * | 2020-01-21 | 2020-06-12 | 北京字节跳动网络技术有限公司 | Text error correction method, device, equipment and medium |
| CN111326144A (en) * | 2020-02-28 | 2020-06-23 | 网易（杭州）网络有限公司 | Voice data processing method, device, medium and computing equipment |
| CN111339757A (en) * | 2020-02-13 | 2020-06-26 | 上海凯岸信息科技有限公司 | Error correction method for voice recognition result in collection scene |
| CN111350249A (en) * | 2020-04-13 | 2020-06-30 | 于巧宇 | Intelligent closestool device based on speech recognition |
| CN111613214A (en) * | 2020-05-21 | 2020-09-01 | 重庆农村商业银行股份有限公司 | Language model error correction method for improving voice recognition capability |
| CN112084775A (en) * | 2020-09-10 | 2020-12-15 | 中航华东光电（上海）有限公司 | Text error correction method after voice conversion |
| CN112560493A (en) * | 2020-12-17 | 2021-03-26 | 金蝶软件（中国）有限公司 | Named entity error correction method, named entity error correction device, computer equipment and storage medium |
| CN112560842A (en) * | 2020-12-07 | 2021-03-26 | 马上消费金融股份有限公司 | Information identification method, device, equipment and readable storage medium |
| WO2021218329A1 (en) * | 2020-04-28 | 2021-11-04 | 深圳壹账通智能科技有限公司 | Parallel corpus generation method, apparatus and device, and storage medium |
| CN113763961A (en) * | 2020-06-02 | 2021-12-07 | 阿里巴巴集团控股有限公司 | Text processing method and device |
| CN113963682A (en) * | 2021-10-22 | 2022-01-21 | 鼎富新动力(北京)智能科技有限公司 | Voice recognition correction method and device, electronic equipment and storage medium |
| CN114091408A (en) * | 2020-08-04 | 2022-02-25 | 科沃斯商用机器人有限公司 | Text correction method, model training method, correction model, equipment and robot |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104464736A (en) * | 2014-12-15 | 2015-03-25 | 北京百度网讯科技有限公司 | Error correction method and device for voice recognition text |
| CN105869642A (en) * | 2016-03-25 | 2016-08-17 | 海信集团有限公司 | Voice text error correction method and device |
| EP3113176A1 (en) * | 2015-06-30 | 2017-01-04 | Samsung Electronics Co., Ltd. | Speech recognition apparatus, speech recognition method, and electronic device |
| CN106297797A (en) * | 2016-07-26 | 2017-01-04 | 百度在线网络技术（北京）有限公司 | Method for correcting error of voice identification result and device |
| CN106847288A (en) * | 2017-02-17 | 2017-06-13 | 上海创米科技有限公司 | The error correction method and device of speech recognition text |
-
2017
- 2017-10-23 CN CN201710994082.XA patent/CN107729321A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104464736A (en) * | 2014-12-15 | 2015-03-25 | 北京百度网讯科技有限公司 | Error correction method and device for voice recognition text |
| EP3113176A1 (en) * | 2015-06-30 | 2017-01-04 | Samsung Electronics Co., Ltd. | Speech recognition apparatus, speech recognition method, and electronic device |
| CN105869642A (en) * | 2016-03-25 | 2016-08-17 | 海信集团有限公司 | Voice text error correction method and device |
| CN106297797A (en) * | 2016-07-26 | 2017-01-04 | 百度在线网络技术（北京）有限公司 | Method for correcting error of voice identification result and device |
| CN106847288A (en) * | 2017-02-17 | 2017-06-13 | 上海创米科技有限公司 | The error correction method and device of speech recognition text |
Cited By (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108694166A (en) * | 2018-04-11 | 2018-10-23 | 广州视源电子科技股份有限公司 | Candidate word evaluation method and device, computer equipment and storage medium |
| CN108595419A (en) * | 2018-04-11 | 2018-09-28 | 广州视源电子科技股份有限公司 | Candidate word evaluation method, candidate word sorting method and device |
| CN108595431A (en) * | 2018-04-28 | 2018-09-28 | 海信集团有限公司 | Interactive voice text error correction method, device, terminal and storage medium |
| CN108804414A (en) * | 2018-05-04 | 2018-11-13 | 科沃斯商用机器人有限公司 | Text modification method, device, smart machine and readable storage medium storing program for executing |
| CN110600005A (en) * | 2018-06-13 | 2019-12-20 | 蔚来汽车有限公司 | Speech recognition error correction method and apparatus, computer device and recording medium |
| CN110600005B (en) * | 2018-06-13 | 2023-09-19 | 蔚来(安徽)控股有限公司 | Speech recognition error correction method and device, computer equipment and recording medium |
| CN108959250A (en) * | 2018-06-27 | 2018-12-07 | 众安信息技术服务有限公司 | A kind of error correction method and its system based on language model and word feature |
| CN109522550A (en) * | 2018-11-08 | 2019-03-26 | 和美（深圳）信息技术股份有限公司 | Text information error correction method, device, computer equipment and storage medium |
| CN109710929A (en) * | 2018-12-18 | 2019-05-03 | 金蝶软件（中国）有限公司 | A kind of bearing calibration, device, computer equipment and the storage medium of speech recognition text |
| CN109684643A (en) * | 2018-12-26 | 2019-04-26 | 湖北亿咖通科技有限公司 | Text recognition method, electronic equipment and computer-readable medium based on sentence vector |
| CN109684643B (en) * | 2018-12-26 | 2021-03-12 | 湖北亿咖通科技有限公司 | Sentence vector-based text recognition method, electronic device and computer-readable medium |
| CN109918485A (en) * | 2019-01-07 | 2019-06-21 | 口碑(上海)信息技术有限公司 | The method and device of speech recognition vegetable, storage medium, electronic device |
| CN109977412A (en) * | 2019-03-29 | 2019-07-05 | 北京林业大学 | A kind of field value error correction method, device, readable medium and storage control |
| CN109977412B (en) * | 2019-03-29 | 2022-12-27 | 北京林业大学 | Method and device for correcting field value of voice recognition text and storage controller |
| CN110210029A (en) * | 2019-05-30 | 2019-09-06 | 浙江远传信息技术股份有限公司 | Speech text error correction method, system, equipment and medium based on vertical field |
| CN110265019A (en) * | 2019-07-03 | 2019-09-20 | 中通智新(武汉)技术研发有限公司 | A kind of method and speech robot people's system of speech recognition |
| CN110176237A (en) * | 2019-07-09 | 2019-08-27 | 北京金山数字娱乐科技有限公司 | A kind of audio recognition method and device |
| CN110765763B (en) * | 2019-09-24 | 2023-12-12 | 金蝶软件（中国）有限公司 | Error correction method and device for voice recognition text, computer equipment and storage medium |
| CN110765763A (en) * | 2019-09-24 | 2020-02-07 | 金蝶软件（中国）有限公司 | Error correction method and device for speech recognition text, computer equipment and storage medium |
| CN111274785A (en) * | 2020-01-21 | 2020-06-12 | 北京字节跳动网络技术有限公司 | Text error correction method, device, equipment and medium |
| CN111274785B (en) * | 2020-01-21 | 2023-06-20 | 北京字节跳动网络技术有限公司 | Text error correction method, device, equipment and medium |
| CN111339757A (en) * | 2020-02-13 | 2020-06-26 | 上海凯岸信息科技有限公司 | Error correction method for voice recognition result in collection scene |
| CN111326144A (en) * | 2020-02-28 | 2020-06-23 | 网易（杭州）网络有限公司 | Voice data processing method, device, medium and computing equipment |
| CN111326144B (en) * | 2020-02-28 | 2023-03-03 | 网易（杭州）网络有限公司 | Voice data processing method, device, medium and computing equipment |
| CN111350249A (en) * | 2020-04-13 | 2020-06-30 | 于巧宇 | Intelligent closestool device based on speech recognition |
| WO2021218329A1 (en) * | 2020-04-28 | 2021-11-04 | 深圳壹账通智能科技有限公司 | Parallel corpus generation method, apparatus and device, and storage medium |
| CN111613214A (en) * | 2020-05-21 | 2020-09-01 | 重庆农村商业银行股份有限公司 | Language model error correction method for improving voice recognition capability |
| CN113763961A (en) * | 2020-06-02 | 2021-12-07 | 阿里巴巴集团控股有限公司 | Text processing method and device |
| CN113763961B (en) * | 2020-06-02 | 2024-04-09 | 阿里巴巴集团控股有限公司 | Text processing method and device |
| CN114091408A (en) * | 2020-08-04 | 2022-02-25 | 科沃斯商用机器人有限公司 | Text correction method, model training method, correction model, equipment and robot |
| CN112084775B (en) * | 2020-09-10 | 2021-09-07 | 中航华东光电（上海）有限公司 | Text error correction method after voice conversion |
| CN112084775A (en) * | 2020-09-10 | 2020-12-15 | 中航华东光电（上海）有限公司 | Text error correction method after voice conversion |
| CN112560842A (en) * | 2020-12-07 | 2021-03-26 | 马上消费金融股份有限公司 | Information identification method, device, equipment and readable storage medium |
| CN112560493A (en) * | 2020-12-17 | 2021-03-26 | 金蝶软件（中国）有限公司 | Named entity error correction method, named entity error correction device, computer equipment and storage medium |
| CN112560493B (en) * | 2020-12-17 | 2024-04-30 | 金蝶软件（中国）有限公司 | Named entity error correction method, named entity error correction device, named entity error correction computer equipment and named entity error correction storage medium |
| CN113963682A (en) * | 2021-10-22 | 2022-01-21 | 鼎富新动力(北京)智能科技有限公司 | Voice recognition correction method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107729321A (en) | A kind of method for correcting error of voice identification result | |
| US8719021B2 (en) | Speech recognition dictionary compilation assisting system, speech recognition dictionary compilation assisting method and speech recognition dictionary compilation assisting program | |
| CN104166462B (en) | The input method and system of a kind of word | |
| US7412387B2 (en) | Automatic improvement of spoken language | |
| US8126714B2 (en) | Voice search device | |
| US8073677B2 (en) | Speech translation apparatus, method and computer readable medium for receiving a spoken language and translating to an equivalent target language | |
| CN105404621B (en) | A kind of method and system that Chinese character is read for blind person | |
| CN109637537B (en) | Method for automatically acquiring annotated data to optimize user-defined awakening model | |
| KR100825690B1 (en) | Error correction method in speech recognition system | |
| Smith | Limits on the application of frequency-based language models to OCR | |
| JPWO2016067418A1 (en) | Dialog control apparatus and dialog control method | |
| JP2009140503A (en) | Method and apparatus for translating speech | |
| CN111985234B (en) | Voice text error correction method | |
| CN110942767B (en) | Recognition labeling and optimization method and device for ASR language model | |
| CN111613214A (en) | Language model error correction method for improving voice recognition capability | |
| CN111883137A (en) | Text processing method and device based on voice recognition | |
| CN104050255A (en) | Joint graph model-based error correction method and system | |
| Abandah et al. | Investigating hybrid approaches for Arabic text diacritization with recurrent neural networks | |
| US8335681B2 (en) | Machine-translation apparatus using multi-stage verbal-phrase patterns, methods for applying and extracting multi-stage verbal-phrase patterns | |
| CN112489655A (en) | Method, system and storage medium for correcting error of speech recognition text in specific field | |
| Rasooli et al. | Unsupervised morphology-based vocabulary expansion | |
| Ostrogonac et al. | Morphology-based vs unsupervised word clustering for training language models for Serbian | |
| Hanzlíček et al. | Using LSTM neural networks for cross‐lingual phonetic speech segmentation with an iterative correction procedure | |
| CN111898342A (en) | Chinese pronunciation verification method based on edit distance | |
| Neubig et al. | Improved statistical models for SMT-based speaking style transformation |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20180604 Address after: 200126 Yaohua Road, Pudong New Area, Shanghai, Room 204, room 560 Applicant after: Ye Wei Address before: 200050 West Yan'an Road, Changning District, Changning District, Shanghai, 4 Applicant before: Shanghai Century Network Technology Co., Ltd. |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20190404 Address after: Room 1287, 1/1, 8 Block 33 Guangshun Road, Changning District, Shanghai, 2003 Applicant after: Shanghai Century Network Technology Co., Ltd. Address before: 200126 Yaohua Road, Pudong New Area, Shanghai, Room 204, room 560 Applicant before: Ye Wei |
|
| TA01 | Transfer of patent application right | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180223 |
|
| RJ01 | Rejection of invention patent application after publication |