Multi-stream end-To-end speech recognition

Ruizhi Li*, Xiaofei Wang, Sri Harish Mallidi, Shinji Watanabe, Takaaki Hori, Hynek Hermansky

*この研究の対応する著者

研究成果: Article査読

9 被引用数 (Scopus)

抄録

Attention-based methods and Connectionist Temporal Classification (CTC) network have been promising research directions for end-To-end (E2E) Automatic Speech Recognition (ASR). The joint CTC/Attention model has achieved great success by utilizing both architectures during multi-Task training and joint decoding. In this article, we present a multi-stream framework based on joint CTC/Attention E2E ASR with parallel streams represented by separate encoders aiming to capture diverse information. On top of the regular attention networks, the Hierarchical Attention Network (HAN) is introduced to steer the decoder toward the most informative encoders. A separate CTC network is assigned to each stream to force monotonic alignments. Two representative framework have been proposed and discussed, which are Multi-Encoder Multi-Resolution (MEM-Res) framework and Multi-Encoder Multi-Array (MEM-Array) framework, respectively. In MEM-Res framework, two heterogeneous encoders with different architectures, temporal resolutions and separate CTC networks work in parallel to extract complementary information from same acoustics. Experiments are conducted on Wall Street Journal (WSJ) and CHiME-4, resulting in relative Word Error Rate (WER) reduction of \text{18.0}\!-\!\text{32.1}\% and the best WER of \text{3.6}\% in the WSJ eval92 test set. The MEM-Array framework aims at improving the far-field ASR robustness using multiple microphone arrays which are activated by separate encoders. Compared with the best single-Array results, the proposed framework has achieved relative WER reduction of \text{3.7}\% and \text{9.7}\% in AMI and DIRHA multi-Array corpora, respectively, which also outperforms conventional fusion strategies.

本文言語English
論文番号8932598
ページ(範囲)646-655
ページ数10
ジャーナルIEEE/ACM Transactions on Audio Speech and Language Processing
28
DOI
出版ステータスPublished - 2020
外部発表はい

ASJC Scopus subject areas

  • コンピュータ サイエンス(その他)
  • 音響学および超音波学
  • 計算数学
  • 電子工学および電気工学

フィンガープリント

「Multi-stream end-To-end speech recognition」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル