Abstract
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.
Original language | English |
---|---|
Title of host publication | 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 708-712 |
Number of pages | 5 |
Volume | 2015-August |
ISBN (Electronic) | 9781467369978 |
DOIs | |
Publication status | Published - 2015 Aug 4 |
Externally published | Yes |
Event | 40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Brisbane, Australia Duration: 2014 Apr 19 → 2014 Apr 24 |
Other
Other | 40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 |
---|---|
Country/Territory | Australia |
City | Brisbane |
Period | 14/4/19 → 14/4/24 |
Keywords
- ASR
- deep networks
- LSTM
- speech enhancement
- speech separation
ASJC Scopus subject areas
- Signal Processing
- Software
- Electrical and Electronic Engineering