Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
| Paper: | SP-P15.6 |
| Session: | Robustness in Noisy Environments |
| Time: | Friday, May 21, 15:30 - 17:30 |
| Presentation: |
Poster |
| Topic: |
Speech Processing: Robust Speech Recognition |
| Title: |
UNIVERSAL COMPENSATION - AN APPROACH TO NOISY SPEECH RECOGNITION ASSUMING NO KNOWLEDGE OF NOISE |
| Authors: |
Ji Ming; Queen's University Belfast | | |
| Abstract: |
We aim to develop an acoustic model for noisy speech recognition that is ''trained once, suits all'', in terms of offering a recognition performance close to the matched training-testing condition performance based only on clean speech training data. This paper describes such a method termed Universal Compensation, for its ability to accommodate arbitrary additive noise without assuming any knowledge about the noise. The new UC method consists of two parts: 1) converting full-band spectral corruption into partial-band spectral corruption via compensations for simulated wide-band flat-spectrum noise at consecutive SNRs (signal-to-noise ratios), and 2) reducing the effect of the remaining partial frequency-band corruption on recognition by ignoring the severely mismatched spectral components and basing the recognition mainly on the matched or least distorted spectral components. Experiments on Aurora 2 indicate that the new model, trained from clean data, has achieved an accuracy comparable to or better than the accuracy achieved by the baseline system trained on multi-condition data; experiments with noises unseen in Aurora 2 have shown significant improvement for the new model over the baseline model with multi-condition training. |
| |
| Back | |