Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks

Hakan Erdogan, John R. Hershey, Shinji Watanabe, Jonathan Le Roux

研究成果: Conference contribution

324 被引用数 (Scopus)

抄録

Separation of speech embedded in non-stationary interference is a challenging problem that has recently seen dramatic improvements using deep network-based methods. Previous work has shown that estimating a masking function to be applied to the noisy spectrum is a viable approach that can be improved by using a signal-approximation based objective function. Better modeling of dynamics through deep recurrent networks has also been shown to improve performance. Here we pursue both of these directions. We develop a phase-sensitive objective function based on the signal-to-noise ratio (SNR) of the reconstructed signal, and show that in experiments it yields uniformly better results in terms of signal-to-distortion ratio (SDR). We also investigate improvements to the modeling of dynamics, using bidirectional recurrent networks, as well as by incorporating speech recognition outputs in the form of alignment vectors concatenated with the spectral input features. Both methods yield further improvements, pointing to tighter integration of recognition with separation as a promising future direction.

本文言語English
ホスト出版物のタイトル2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings
出版社Institute of Electrical and Electronics Engineers Inc.
ページ708-712
ページ数5
2015-August
ISBN(電子版)9781467369978
DOI
出版ステータスPublished - 2015 8 4
外部発表はい
イベント40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Brisbane, Australia
継続期間: 2014 4 192014 4 24

Other

Other40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015
CountryAustralia
CityBrisbane
Period14/4/1914/4/24

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

フィンガープリント 「Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks」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