Exemplar-based speech enhancement for deep neural network based automatic speech recognition
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review
Details
| Original language | English |
|---|---|
| Title of host publication | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings |
| Publisher | The Institute of Electrical and Electronics Engineers, Inc. |
| Pages | 4485-4489 |
| Number of pages | 5 |
| ISBN (Print) | 9781467369978 |
| DOIs | |
| Publication status | Published - 4 Aug 2015 |
| Publication type | A4 Article in a conference publication |
| Event | IEEE International Conference on Acoustics, Speech and Signal Processing - Duration: 1 Jan 1900 → 1 Jan 2000 |
Conference
| Conference | IEEE International Conference on Acoustics, Speech and Signal Processing |
|---|---|
| Period | 1/01/00 → 1/01/00 |
Abstract
Deep neural network (DNN) based acoustic modelling has been successfully used for a variety of automatic speech recognition (ASR) tasks, thanks to its ability to learn higher-level information using multiple hidden layers. This paper investigates the recently proposed exemplar-based speech enhancement technique using coupled dictionaries as a pre-processing stage for DNN-based systems. In this setting, the noisy speech is decomposed as a weighted sum of atoms in an input dictionary containing exemplars sampled from a domain of choice, and the resulting weights are applied to a coupled output dictionary containing exemplars sampled in the short-time Fourier transform (STFT) domain to directly obtain the speech and noise estimates for speech enhancement. In this work, settings using input dictionary of exemplars sampled from the STFT, Mel-integrated magnitude STFT and modulation envelope spectra are evaluated. Experiments performed on the AURORA-4 database revealed that these pre-processing stages can improve the performance of the DNN-HMM-based ASR systems with both clean and multi-condition training.
ASJC Scopus subject areas
Keywords
- coupled dictionaries, deep neural networks, modulation envelope, non-negative matrix factorisation, speech enhancement