Detail publikace

Analysis of Multilingual Sequence-to-Sequence Speech Recognition Systems

KARAFIÁT, M. BASKAR, M. WATANABE, S. HORI, T. WIESNER, M. ČERNOCKÝ, J.

Originální název

Analysis of Multilingual Sequence-to-Sequence Speech Recognition Systems

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

This paper investigates the applications of various multilingual approaches developed in conventional deep neural network - hidden Markov model (DNN-HMM) systems to sequence-tosequence (seq2seq) automatic speech recognition (ASR). We employ a joint connectionist temporal classification-attention network as our base model. Our main contribution is separated into two parts. First, we investigate the effectiveness of the seq2seq model with stacked multilingual bottle-neck features obtained from a conventional DNN-HMM system on the Babel multilingual speech corpus. Second, we investigate the effectiveness of transfer learning from a pre-trained multilingual seq2seq model with and without the target language included in the original multilingual training data. In this experiment, we also explore various architectures and training strategies of the multilingual seq2seq model by making use of knowledge obtained in the DNN-HMM based transfer-learning. Although both approaches significantly improved the performance from a monolingual seq2seq baseline, interestingly, we found the multilingual bottle-neck features to be superior to multilingual models with transfer learning. This finding suggests that we can efficiently combine the benefits of the DNN-HMM system with the seq2seq system through multilingual bottle-neck feature techniques.

Klíčová slova

multilingual ASR, sequence-to-sequence, language-transfer, multilingual bottle-neck feature

Autoři

KARAFIÁT, M.; BASKAR, M.; WATANABE, S.; HORI, T.; WIESNER, M.; ČERNOCKÝ, J.

Vydáno

15. 9. 2019

Nakladatel

International Speech Communication Association

Místo

Graz

ISSN

1990-9772

Periodikum

Proceedings of Interspeech

Ročník

2019

Číslo

9

Stát

Francouzská republika

Strany od

2220

Strany do

2224

Strany počet

5

URL

https://www.isca-speech.org/archive/Interspeech_2019/pdfs/2355.pdf

BibTex

@inproceedings{BUT159995,
  author="KARAFIÁT, M. and BASKAR, M. and WATANABE, S. and HORI, T. and WIESNER, M. and ČERNOCKÝ, J.",
  title="Analysis of Multilingual Sequence-to-Sequence Speech Recognition Systems",
  booktitle="Proceedings of Interspeech",
  year="2019",
  journal="Proceedings of Interspeech",
  volume="2019",
  number="9",
  pages="2220--2224",
  publisher="International Speech Communication Association",
  address="Graz",
  doi="10.21437/Interspeech.2019-2355",
  issn="1990-9772",
  url="https://www.isca-speech.org/archive/Interspeech_2019/pdfs/2355.pdf"
}