Grant-in-Aid for General Scientific Research (B)
|Allocation Type||Single-year Grants |
|Research Institution||KYOTO UNIVERSITY |
DOSHITA Shuji Kyoto Univ. Faculty of Engineering Professor, 工学部, 教授 (00025925)
ISHIBASHI Hayato Kyoto Univ. Data Processing Center Assistant Professor, 大型計算機センター, 助手 (70212925)
KAWAHARA Tatsuya Kyoto Univ. Faculty of Engineering Assistant Professor, 工学部, 助手 (00234104)
KITAZAWA Shigeyoshi Shizuoka Univ. Faculty of Engineering Associate Professor, 工学部, 助教授 (00109018)
YAMADA Atsushi Kyoto Univ. Faculty of Engineering Assistant Professor, 工学部, 助手 (20240004)
NISHIDA Toyoaki Kyoto Univ. Faculty of Engineering Associate Professor, 工学部, 助教授 (70135531)
|Project Period (FY)
1990 – 1992
Completed (Fiscal Year 1992)
|Budget Amount *help
¥6,400,000 (Direct Cost: ¥6,400,000)
Fiscal Year 1992: ¥1,500,000 (Direct Cost: ¥1,500,000)
Fiscal Year 1991: ¥1,800,000 (Direct Cost: ¥1,800,000)
Fiscal Year 1990: ¥3,100,000 (Direct Cost: ¥3,100,000)
|Keywords||Pattern Understanding / Speech Recognition / Speech Understanding / HMM / Context-Free Grammar / Keyword Spotting / Semantic Network / A^*Search / 音声対話 / キ-ワ-ド抽出 / 確率文脈自由文法 / 意味ネットワ-ク / 確率的推論 / 論理的推論 / 自然言語理解 / ベイズ識別器 / ATMS / 概念ネットワ-ク|
For intelligent speech recognition and understanding, we have examined reasoning strategies on several knowledge-levels, and integrated them into speech understanding systems as follows:
(1) Phoneme recognition
We have firstly improved phoneme recognition, which is the base of the whole system. Phoneme HMM based on pair-wise Bayes classifiers is proposed with 27 phoneme recognition rate of 83.1% and 653 word recognition rate of 84.8%.
(2) Syntactic analysis
Syntactic analyzer is developed by integrating probabilistic reasoning and symbolic reasoning on vocabulary and syntax level. Here heuristic search is performed based on prediction by syntax rules and probabilities of HMM. A^*-admissible context-free parsing with word-pair constraints as heuristics is presented.
(3) Keyword spotting
It is possible to make sense of sentences with multiple keywords, without syntax rules. However, conventional method extracts keywords using only the scores of their own, thus insufficient. A new spotting algorithm is presented with assumes logical constraint that the input is a phoneme or word sequence containing target keywords.
(4) Semantic analysis
Network-based semantic analyzer is developed which accepts both N-best word sequences and a keyword lattice and obtains a semantic representation. Here semantic, pragmatic and dialog-level knowledge is integrated and plausible hypothesis is obtained by combining probabilities of candidate words.
(5) Speech understanding system
Two reasoning strategies are implemented on speech understanding systems. One is syntactic-driven which integrates (1), (2) and (4). The other is semantic-driven which integrates (1), (3) and (4). We have evaluated both systems on a task whose vocabulary size is 244 and word perplexity is 80. For grammatical utterances, syntactic-driven approach got an accuracy of 65.5%, while semantic-driven achieved just 44.0%. However, semantic-driven approach is effective for out-of-grammar utterances.