| Project/Area Number |
59420031
|
|---|
| Research Category |
Grant-in-Aid for General Scientific Research (A)
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
電子通信系統工学
|
|---|
| Research Institution | TOHOKU UNIVERSITY |
|---|
Principal Investigator |
KIDO Ken'iti Professor, Research Center for Applied Information Sciences, Tohoku University, 国立大学(その他), 教授 (30006209)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
SUZUKI Yoiti Research Associate, Reseach Institute of Electrical Communication, Tohoku Univer, 電気通信研究所, 助手 (20143034)
MIWA Jouji Associate Professor, Faculty of Engineering, Iwate University, 工学部, 助教授 (60125664)
ABE Masato Research Associate, Faculty of Engineering, Tohoku University, 工学部, 助手 (00159443)
MAKINO Shozo Research Associate, Research Center for Applied Information Sciences, Tohoku Uni, 応用情報学研究センター, 助手 (00089806)
|
|---|
| Project Period (FY) |
1984 – 1986
|
| Project Status |
Completed (Fiscal Year 1986)
|
| Budget Amount *help |
¥22,100,000 (Direct Cost: ¥22,100,000)
Fiscal Year 1986: ¥3,000,000 (Direct Cost: ¥3,000,000)
Fiscal Year 1985: ¥3,000,000 (Direct Cost: ¥3,000,000)
Fiscal Year 1984: ¥16,100,000 (Direct Cost: ¥16,100,000)
|
|---|
| Keywords | Speech Recognition / Natural language processing / Syntax processing / Semantic processing / Speaker-independent / 単語スポッテイング / 音声 / 自動認識 / 音声認識 / 意味 / 構文 / 音声データベース / 単語音声 / 文章音声 |
|---|
| Research Abstract |
We have developed a Japanese dictation system which can convert a continuous speech uttered by unspecified speaker to a Kanji-Kana string. The system is composed of an acoustic processing part, a spotting part of Bunsetsu-like units and a syntax and semantic processing part. Our object is to recognize a sentence speech whose syntax and semantic structures are syntactically and semantically reasonable. In the acoustic processing part, an input speech is analized by a 29 channel band-pass filter bank. Segment features are extracted from short-time spectra using time-spectrum patterns and then converted to a phoneme string. In the spotting part of Bunsetsu-like units, Bunsetsu-like units are spotted from a phoneme string using a syntactic driven continuous DP can dominantly reduce the amounts of computation and storage necessary to spot Bunsetsu-like units. Inthe syntactic and semantic processing part, functional features are given to Bunsetsu-like unit candidates from lexical items, where functional features contains syntactic and semantic information. Possibility of concatenation between two adjacent Bunsetsu-like units is checked based on the functional features and then the two adjacent units make a larger unit if satisfying syntactic and semantic reasonability, and thus a complete sentence is finally made.
When a speaker utterd a sentence by a Bunsetsu-like unit, 60% of sentence recognition score is obtained in case of 85% phoneme recognition score. 80% of sentence recognition score is obtained in case of 95% phoneme recognition score. Refining the rules in syntactic and semantic processing part can improve the sentence recognition score.
|
