A Spectrogram Model for Enhanced Source Localization and Noise-Robust ASR
| Type of publication: | Conference paper |
| Citation: | lathoud05c |
| Booktitle: | Proceedings of INTERSPEECH 2005 |
| Year: | 2005 |
| Month: | 9 |
| Address: | Lisbon, Portugal |
| Note: | IDIAP-RR 05-13 |
| Crossref: | lathoud-rr-05-13: |
| Abstract: | This paper proposes a simple, computationally efficient 2-mixture model approach to discrimination between speech and background noise. It is directly derived from observations on real data, and can be used in a fully unsupervised manner, with the EM algorithm. A first application to sector-based, joint audio source localization and detection, using multiple microphones, confirms that the model can provide major enhancement. A second application to the single channel speech recognition task in a noisy environment yields major improvement on stationary noise and promising results on non-stationary noise. |
| Userfields: | ipdinar={2005}, ipdmembership={speech}, |
| Keywords: | |
| Projects: |
Idiap |
| Authors: | |
| Added by: | [UNK] |
| Total mark: | 0 |
|
Attachments
|
|
|
|
|
Notes
|
|
|
|
|
