Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
| Paper: | SP-L9.6 |
| Session: | Robust Features for Speech Recognition |
| Time: | Friday, May 21, 14:40 - 15:00 |
| Presentation: |
Lecture |
| Topic: |
Speech Processing: Robust Speech Recognition |
| Title: |
ROBUST SPEECH RECOGNITION USING CEPSTRAL DOMAIN MISSING DATA TECHNIQUES AND NOISY MASKS |
| Authors: |
Hugo Van hamme; Katholieke Universiteit Leuven | | |
| Abstract: |
Missing Data Techniques (MDT) have shown to be an effective method for curing the performance degradation of HMM-based speech recognition systems operating on noisy signals. However, a major drawback of the approach is that MDT requires that the acoustic model be expressed as a mixture of diagonal Gaussians in the log-spectral domain, whereas a higher accuracy can be obtained with Gaussian mixtures in the cepstral domain. This paper describes a recognizer based on the recently described cepstral-domain MDT approach using missing data masks computed from the noisy signal. It exploits a novel decision criterion that integrates harmonicity with signal-to-noise ratio and which makes minimal assumptions on the noise. The system is shown to exhibit a recognition accuracy that is comparable to the ETSI Advanced Front-End reference. |
| |
| Back | |