Presentation | 1997/6/19 Phoneme Boundary Estimation using Recurrent Neural Networks and Its Application to Speech Recognition Toshiaki Fukada, Sophie Aveline, Mike Schuster, Yoshinori Sagisaka, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | This paper describes a phoneme boundary estimation method based on recurrent neural networks (RNNs). The proposed method only requires acoustic observations to accurately estimate segment boundaries. Experimental results showed that the proposed method could estimate segment boundaries significantly better than an HMM or an MLP (multi-layer perceptron) based method. Furthermore, we incorporated the RNN based segment boundary estimator into the HMM based and segment based recognition systems. As a result, we confirmed that (1) the usage of BRNN outputs was effective for improving the recognition rate and reducing computational time in an HMM based recognition system and (2) segment lattices obtained by the proposed methods dramatically reduce the computational complexity of segment model based recognition. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | phoneme boundary / recurrent neural networks / HMM / segment model / speech recognition |
Paper # | SP97-15 |
Date of Issue |
Conference Information | |
Committee | SP |
---|---|
Conference Date | 1997/6/19(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Speech (SP) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Phoneme Boundary Estimation using Recurrent Neural Networks and Its Application to Speech Recognition |
Sub Title (in English) | |
Keyword(1) | phoneme boundary |
Keyword(2) | recurrent neural networks |
Keyword(3) | HMM |
Keyword(4) | segment model |
Keyword(5) | speech recognition |
1st Author's Name | Toshiaki Fukada |
1st Author's Affiliation | ATR Interpreting Telecommunications Research Laboratories() |
2nd Author's Name | Sophie Aveline |
2nd Author's Affiliation | ATR Interpreting Telecommunications Research Laboratories |
3rd Author's Name | Mike Schuster |
3rd Author's Affiliation | ATR Interpreting Telecommunications Research Laboratories |
4th Author's Name | Yoshinori Sagisaka |
4th Author's Affiliation | ATR Interpreting Telecommunications Research Laboratories |
Date | 1997/6/19 |
Paper # | SP97-15 |
Volume (vol) | vol.97 |
Number (no) | 114 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |