Pushing the Envelope â€” Aside
Nelson Morgan; Qifeng Zhu; Andreas Stolcke; Kemal SÃ¶nmez; Sunil Sivadas; Takahiro Shinozaki; Mari Ostendorf; Pratibha Jain; Hynek Hermansky; Daniel P. W. Ellis; George Doddington; Barry Chen; Ã–zgÃ¼r Ã‡etin; HervÃ© Bourlard; Marios Athineos
- Pushing the Envelope â€” Aside
Ellis, Daniel P. W.
- Electrical Engineering
- Permanent URL:
- Book/Journal Title:
- IEEE Signal Processing Magazine
- Despite successes, there are still significant limitations to speech recognition performance, particularly for conversational speech and/or for speech with significant acoustic degradations from noise or reverberation. For this reason, authors have proposed methods that incorporate different (and larger) analysis windows, which are described in this article. Note in passing that we and many others have already taken advantage of processing techniques that incorporate information over long time ranges, for instance for normalization (by cepstral mean subtraction as stated in B. Atal (1974) or relative spectral analysis (RASTA) based in H. Hermansky and N. Morgan (1994)). They also have proposed features that are based on speech sound class posterior probabilities, which have good properties for both classification and stream combination.
- Item views: