Name
Title | ||
|---|---|---|
Unsupervised And Incremental Speaker Adaptation Under Adverse Environmental Conditions |
Abstract | ||
|---|---|---|
A new speaker adaptation method is described. In practical applications of speaker adaptation, adaptation and testing environments change significantly and are unknown beforehand. In such cases, since the speaker adaptation adapts a reference pattern to the adaptation utterances in regard to differences in both environment and speaker at the same time, performance in speaker adaptation would be degraded. To cope with this problem, our proposed method first eliminates the environmental differences between een each input utterance and a reference pattern by using a, rapid environment adaptation algorithm based on spectrum equalization (REALISE) [2]. Then we apply an unsupervised and incremental speaker adaptation with autonomous control using tree structure pdfs (ACTS) [1] to the environmentally adapted reference pattern. fly combining these two methods, the resulting system is expected to perform well under adverse environmental conditions and to show a stable improvement regardless of the amount of adaptation data. Evaluation experiments were carried out for utterances under three vehicle speed conditions. Recognition rates for a 100-Japanese-word recognition task after 100-word adaptation were improved from 92% (ACTS alone) to 95% (proposed method). |
Year | DOI | Venue |
|---|---|---|
1996 | 10.1109/ICSLP.1996.607211 | ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4 |
Keywords | Field | DocType |
tree structure,probability density function,information technology,degradation,testing,national electric code,speech processing,natural languages,speech recognition,word recognition,adaptive systems,probability,spectrum,tree data structures | Speech processing,Equalization (audio),Pattern recognition,Adaptive system,Computer science,Tree (data structure),Word recognition,Speech recognition,Speaker recognition,Natural language,Tree structure,Artificial intelligence | Conference |
Citations | PageRank | References |
0 | 0.34 | 5 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Keizaburo Takagi | 1 | 19 | 4.65 |
| Koichi Shinoda | 2 | 463 | 65.14 |
| Hiroaki Hattori | 3 | 21 | 4.39 |
| Takao Watanabe | 4 | 107 | 14.18 |