logo Idiap Research Institute        
 [BibTeX] [Marc21]
Recognition Of Reverberant Speech Using Frequency Domain Linear Prediction
Type of publication: Journal paper
Citation: tsamuel:ieee-letters:2008
Journal: IEEE Signal Processing Letters
Year: 2008
Note: IDIAP-RR 08-41
Crossref: tsamuel:rr08-41:
Abstract: Performance of a typical automatic speech recognition (ASR) system severely degrades when it encounters speech from reverberant environments. Part of the reason for this degradation is the feature extraction techniques that use analysis windows which are much shorter than typical room impulse responses. We present a feature extraction technique based on modeling temporal envelopes of the speech signal in narrow sub-bands using Frequency Domain Linear Prediction (FDLP). FDLP provides an all-pole approximation of the Hilbert envelope of the signal obtained by linear prediction on cosine transform of the signal. ASR experiments on speech data degraded with a number of room impulse responses (with varying degrees of distortion) show significant performance improvements for the proposed FDLP features when compared to other robust feature extraction techniques (average relative reduction of $24 \%$ in word error rate). Similar improvements are also obtained for far-field data which contain natural reverberation in background noise. These results are achieved without any noticeable degradation in performance for clean speech.
Userfields: ipdmembership={speech},
Projects Idiap
Authors Thomas, Samuel
Ganapathy, Sriram
Hermansky, Hynek
Added by: [UNK]
Total mark: 0
  • tsamuel-ieee-letters-2008.pdf
  • tsamuel-ieee-letters-2008.ps.gz