JP2005164837A5 - - Google Patents
Download PDFInfo
- Publication number
- JP2005164837A5 JP2005164837A5 JP2003401724A JP2003401724A JP2005164837A5 JP 2005164837 A5 JP2005164837 A5 JP 2005164837A5 JP 2003401724 A JP2003401724 A JP 2003401724A JP 2003401724 A JP2003401724 A JP 2003401724A JP 2005164837 A5 JP2005164837 A5 JP 2005164837A5
- Authority
- JP
- Japan
- Prior art keywords
- word
- speech recognition
- recognition result
- posterior probability
- generalized
- 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.)
- Granted
Links
Claims (7)
前記音声認識結果に含まれる各単語について、前記音声認識結果に含まれる単語の単語事後確率に基づいて一般化単語事後確率を算出するための一般化単語事後確率算出手段と、
前記音声認識結果に含まれる各単語の単語事後確率を、前記一般化単語事後確率算出手段により算出された一般化単語事後確率で更新するための更新手段と、
前記更新手段により単語事後確率が更新された前記音声認識結果に基づき、前記複数の仮説単語列の中で、当該仮説単語列に含まれる単語の単語事後確率の和が最大となるものを探索するための探索手段と、
前記探索手段により探索された仮説単語列の単語事後確率の和が所定の条件を充足するか否かを判定することにより、前記音声認識結果の信頼度を検証するための判定手段とを含む、音声認識結果の信頼度検証装置。 Receiving a speech recognition result representing a plurality of hypothesized word strings each consisting of a word to which a word posterior probability is given, output from the speech recognition decoder, and verifying the reliability of the speech recognition result based on the word posterior probability A speech recognition result reliability verification device for
For each word included in the speech recognition result, generalized word posterior probability calculating means for calculating a generalized word posterior probability based on the word posterior probability of the word included in the speech recognition result;
Updating means for updating the word posterior probability of each word included in the speech recognition result with the generalized word posterior probability calculated by the generalized word posterior probability calculating means;
Based on the speech recognition result in which the word posterior probability is updated by the updating means, a search is made among the plurality of hypothesis word strings for which the sum of the word posterior probabilities of the words included in the hypothesis word string is maximized. Search means for,
Determination means for verifying the reliability of the speech recognition result by determining whether or not the sum of the word posterior probabilities of the hypothesis word string searched by the search means satisfies a predetermined condition, Reliability verification device for speech recognition results.
前記一般化単語事後確率算出手段は、
前記音声認識結果中に含まれる各単語について、当該単語の時間期間と重なる時間期間であって、かつ当該単語と一致する単語を前記音声認識結果中で検索ための単語検索手段と、
前記単語検索手段により検索された単語の単語事後確率の総和と、前記音声認識結果に含まれる全ての単語の単語事後確率の総和とに基づいて、前記各単語の一般化単語事後確率を算出するための手段とを含む、請求項1又は請求項2に記載の音声認識結果の信頼度検証装置。 Each word included in the speech recognition result is further provided with information for determining a time period during the input utterance to the speech recognition decoder,
The generalized word posterior probability calculating means is:
For each word included in the speech recognition result, a word search means for searching for a word in the speech recognition result that has a time period overlapping with the time period of the word and matches the word,
Based on the sum of the word posterior probabilities of the words searched by the word search means and the sum of the word posterior probabilities of all words included in the speech recognition result, the generalized word posterior probability of each word is calculated. The speech recognition result reliability verification apparatus according to claim 1 or 2, further comprising:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2003401724A JP4478925B2 (en) | 2003-12-01 | 2003-12-01 | Speech recognition result reliability verification apparatus, computer program, and computer |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2003401724A JP4478925B2 (en) | 2003-12-01 | 2003-12-01 | Speech recognition result reliability verification apparatus, computer program, and computer |
Publications (3)
Publication Number | Publication Date |
---|---|
JP2005164837A JP2005164837A (en) | 2005-06-23 |
JP2005164837A5 true JP2005164837A5 (en) | 2005-09-22 |
JP4478925B2 JP4478925B2 (en) | 2010-06-09 |
Family
ID=34725558
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
JP2003401724A Expired - Fee Related JP4478925B2 (en) | 2003-12-01 | 2003-12-01 | Speech recognition result reliability verification apparatus, computer program, and computer |
Country Status (1)
Country | Link |
---|---|
JP (1) | JP4478925B2 (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4659541B2 (en) * | 2005-07-11 | 2011-03-30 | 日本放送協会 | Speech recognition apparatus and speech recognition program |
JP4816409B2 (en) | 2006-01-10 | 2011-11-16 | 日産自動車株式会社 | Recognition dictionary system and updating method thereof |
JP4836076B2 (en) * | 2006-02-23 | 2011-12-14 | 株式会社国際電気通信基礎技術研究所 | Speech recognition system and computer program |
JP4947545B2 (en) * | 2006-08-30 | 2012-06-06 | 株式会社国際電気通信基礎技術研究所 | Speech recognition apparatus and computer program |
-
2003
- 2003-12-01 JP JP2003401724A patent/JP4478925B2/en not_active Expired - Fee Related
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20230206914A1 (en) | Efficient empirical determination, computation, and use of acoustic confusability measures | |
Ferrer et al. | Is the speaker done yet? Faster and more accurate end-of-utterance detection using prosody | |
Chen et al. | Query-by-example keyword spotting using long short-term memory networks | |
US6873993B2 (en) | Indexing method and apparatus | |
JP5048934B2 (en) | Method and apparatus for providing recognition of proper names or partial proper names | |
US6985861B2 (en) | Systems and methods for combining subword recognition and whole word recognition of a spoken input | |
US5797123A (en) | Method of key-phase detection and verification for flexible speech understanding | |
Parlak et al. | Spoken term detection for Turkish broadcast news | |
US6044337A (en) | Selection of superwords based on criteria relevant to both speech recognition and understanding | |
US11024298B2 (en) | Methods and apparatus for speech recognition using a garbage model | |
US7286984B1 (en) | Method and system for automatically detecting morphemes in a task classification system using lattices | |
Ferrer et al. | A prosody-based approach to end-of-utterance detection that does not require speech recognition | |
US8108215B2 (en) | Speech recognition apparatus and method | |
Alon et al. | Contextual speech recognition with difficult negative training examples | |
Schwartz et al. | Multiple-pass search strategies | |
WO2004066268A2 (en) | Dual search acceleration technique for speech recognition | |
JP2001092496A (en) | Continuous voice recognition device and recording medium | |
CN113574545A (en) | Training data modification for training models | |
US20170270923A1 (en) | Voice processing device and voice processing method | |
JP5360414B2 (en) | Keyword extraction model learning system, method and program | |
US20040148169A1 (en) | Speech recognition with shadow modeling | |
JP2005164837A5 (en) | ||
Ramesh et al. | Context dependent anti subword modeling for utterance verification. | |
Vozila et al. | Grapheme to phoneme conversion and dictionary verification using graphonemes. | |
JP2015118354A (en) | Speech recognition device and speech recognition method |