Loading...
Please wait, while we are loading the content...
Similar Documents
Robust AMFM Features for Speech Recognition (2005)
| Content Provider | CiteSeerX |
|---|---|
| Author | Dimitriadis, Dimitrios Maragos, Petros Potamianos, Ros |
| Abstract | Abstract—In this letter, a nonlinear AM-FM speech model is used to extract robust features for speech recognition. The proposed features measure the amount of amplitude and frequency modulation that exists in speech resonances and attempt to model aspects of the speech acoustic information that the commonly used linear source-filter model fails to capture. The robustness and discriminability of the AM-FM features is investigated in combination with mel cepstrum coefficients (MFCCs). It is shown that these hybrid features perform well in the presence of noise, both in terms of phoneme-discrimination (J-measure) and in terms of speech recognition performance in several different tasks. Average relative error rate reduction up to 11 % for clean and 46 % for mismatched noisy conditions is achieved when AM-FM features are combined with MFCCs. |
| File Format | |
| Journal | IEEE Signal Processing Letters |
| Publisher Date | 2005-01-01 |
| Access Restriction | Open |
| Subject Keyword | Robust Amfm Feature Speech Recognition Several Different Task Robust Feature Average Relative Error Rate Reduction Speech Resonance Hybrid Feature Linear Source-filter Model Frequency Modulation Mel Cepstrum Coefficient Noisy Condition Nonlinear Am-fm Speech Model Speech Recognition Performance Am-fm Feature Speech Acoustic Information |
| Content Type | Text |
