ROBUST SPEECH RECOGNITION USING A VOICED-UNVOICED FEATURE [1 citations — 1 self]
Download:
|
|
by Andr As Zolnay, Ralf Schl Uter, Hermann Ney
http://www-i6.informatik.rwth-aachen.de/PostScript/InterneArbeiten/Zolnay_Robust_Speech_Recognition_Using_a_Voiced_Unvoiced_Feature_ICSLP2002.ps
Add To MetaCart
Abstract:
In this paper, a voiced-unvoiced measure is used as acoustic feature for continuous speech recognition. The voiced-unvoiced measure was combined with the standard Mel Frequency Cepstral Coefficients (MFCC) using linear discriminant analysis (LDA) to choose the most relevant features. Experiments were performed on the SieTill (German digit strings recorded over telephone line) and on the SPINE (English spontaneous speech under different simulated noisy environments) corpus. The additional voiced-unvoiced measure results in improvements in word error rate (WER) of up to 11 % relative to using MFCC alone with the same overall number of parameters in the system.
Citations
| 9 | Perceptual harmonic cepstral coefficients as the front-end for speech recognition – Gu, Rose - 2000 |
| 9 | Comparison of Optimization Methods for Discriminative Training Criteria – Schluter, Macherey, et al. - 1997 |
| 6 | Cepstrum-based pitch detection using a new statistical V/UV classification algorithm – Ahmadi, Spanias - 1999 |
| 6 | Incorporating Voice Onset Time to Improve Letter Recognition Accuracies – Niyogi, Ramesh - 1998 |
| 5 | Rabiner and B-H – R - 1993 |
| 2 | Robust Speech Recognition Techniques Applied to a Speech in Noise Task – Rose, Kim, et al. - 2001 |
| 1 | Multistage Coarticulatory Model Combining Articulatory, Formant and Cepstral Features – Gao, Bakis, et al. - 2000 |
