Rapid Speaker Adaptation of Neural Network Based Filterbank Layer for Automatic Speech Recognition
| Autor: | Seiichi Nakagawa, Tomoyosi Akiba, Hiroshi Seki, Kazumasa Yamamoto |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Normalization (statistics)
Artificial neural network Computer science Speech recognition Feature extraction 020206 networking & telecommunications 02 engineering and technology FMLLR Backpropagation 030507 speech-language pathology & audiology 03 medical and health sciences Singular value decomposition 0202 electrical engineering electronic engineering information engineering 0305 other medical science Hidden Markov model Vocal tract |
| Zdroj: | SLT |
| Popis: | Deep neural networks (DNN) have achieved significant success in the field of automatic speech recognition. Previously, we proposed a filterbank-incorporated DNN which takes power spectra as input features. This method has a function of VTLN (Vocal tract length normalization) and fMLLR (feature-space maximum likelihood linear regression). The filterbank layer can be implemented by using a small number of parameters and is optimized under a framework of backpropagation. Therefore, it is advantageous in adaptation under limited available data. In this paper, speaker adaptation is applied to the filterbank-incorporated DNN. By applying speaker adaptation using 15 utterances, the adapted model gave a 7.4% relative improvement in WER over the baseline DNN at a significance level of 0.005 on CSJ task. Adaptation of filterbank layer also showed better performance than the other adaptation methods; singular value decomposition (SVD) based adaptation and learning hidden unit contributions (LHUC). |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|