Name
Title | ||
|---|---|---|
Missing-feature-theory-based robust simultaneous speech recognition system with non-clean speech acoustic model |
Abstract | ||
|---|---|---|
A humanoid robot must recognize a target speech signal while people around the robot chat with them in real-world. To recognize the target speech signal, robot has to separate the target speech signal among other speech signals and recognize the separated speech signal. As separated signal includes distortion, automatic speech recognition (ASR) performance degrades. To avoid the degradation, we trained an acoustic model from non-clean speech signals to adapt acoustic feature of distorted signal and adding white noise to separated speech signal before extracting acoustic feature. The issues are (1) To determine optimal noise level to add the training speech signals, and (2) To determine optimal noise level to add the separated signal. In this paper, we investigate how much noises should be added to clean speech data for training and how speech recognition performance improves for different positions of three talkers with soft masking. Experimental results show that the best performance is obtained by adding white noises of 30 dB. The ASR with the acoustic model outperforms with ASR with the clean acoustic model by 4 points. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1109/IROS.2009.5354201 | IROS |
Keywords | Field | DocType |
target speech signal,speech recognition,missing-feature-theory-based robust simultaneous speech,speech recognition performance,recognition system,speech data,separated speech signal,speech signal,separated signal,training speech signal,robust simultaneous speech recognition system,humanoid robots,missing-feature-theory,nonclean speech acoustic model,non-clean speech acoustic model,humanoid robot,acoustic feature,non-clean speech signal,automatic speech recognition,robots,white noise,hidden markov models,speech | Speech processing,Speech coding,Voice activity detection,Computer science,Speech recognition,White noise,Hidden Markov model,Distortion,Linear predictive coding,Acoustic model | Conference |
ISBN | Citations | PageRank |
978-1-4244-3804-4 | 4 | 0.43 |
References | Authors | |
8 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| toru takahashi | 1 | 337 | 39.39 |
| Kazuhiro Nakadai | 2 | 1342 | 155.91 |
| Kazunori Komatani | 3 | 790 | 87.95 |
| Tetsuya Ogata | 4 | 1158 | 135.73 |
| Hiroshi G. Okuno | 5 | 2092 | 233.19 |