| Project/Area Number |
05452357
|
|---|
| Research Category |
Grant-in-Aid for General Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | KYOTO UNIVERSITY |
|---|
Principal Investigator |
DOSHITA Shuji Fac.Eng., Kyoto Univ., Professor, 工学部, 教授 (00025925)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
ARAKI Masahiro Fac.Eng., Kyoto Univ., Research Associate, 工学部, 助手 (50252490)
KAWAHARA Tatsuya Fac.Eng., Kyoto Univ., Research Associate, 工学部, 助手 (00234104)
北澤 茂良 静岡大学, 工学部, 助教授 (00109018)
|
|---|
| Project Period (FY) |
1993 – 1994
|
| Project Status |
Completed (Fiscal Year 1994)
|
| Budget Amount *help |
¥5,200,000 (Direct Cost: ¥5,200,000)
Fiscal Year 1994: ¥1,500,000 (Direct Cost: ¥1,500,000)
Fiscal Year 1993: ¥3,700,000 (Direct Cost: ¥3,700,000)
|
|---|
| Keywords | Speech Recognition / Natural Language Understanding / Semantic Analysis / Inter-speaker Variation / Robust Parser / ロバストパーサ |
|---|
| Research Abstract |
The aim of this research is to construct a robust speech understanding system against inter-speaker variation and ungrammatical utterances. In order to implement such robust system, we develop a high accuracy speech recognizer with a speaker adaptation method and a semantic driven parsing method.
1.Speaker adaptation of HMM phoneme recognizer
We develop a speaker adaptation method using continuous speech input against inter-speaker variation. We use maximum a posteriori probability estimation to Continuous density Hidden Markov Model (HMM) based on Pair-Wise Bays Classifiers as the phone classifier. We performed experimental evaluation of adaptation to 8 speakers. As a result, the keywords recognition rate of the adapted model of a speaker reached 80.2 %, Which is higher by 11.0 % than that of the baseline model, while the accuracy is lowered for another speaker.
2.Word/Phrase spotting method
Even in spontaneous speech, most words and phrases are correctly uttered. Then, we need a word/phrase spotting method for robust parsing. In order to increase accuracy of these spotter, we develop a heuristic language model that models the rest of target word/phrase. Also, we implement a island-driven praser that can skip filled pauses and unknown words.
Robust speech parser by incremental analysis
In natural dialogues, fragmentary utterances are frequently used. Existing approach can hardly deal with these phenomena because it presupposes a complete sentence input. We try to use incremental parsing method with relaxation to such fragmentary utterances. For implementation, we use marker passer to integrate input fragment to recognized plan structure.
|
