HMM/ANN based spectral peak location estimation for noise robust speech recognition

In this paper, we present an HMM/ANN based algorithm to estimate the spectral peak locations. This algorithm makes use of distinct time-frequency (TF) patterns in the spectrogram for estimating the peak locations. Such a use of TF patterns is expected to impose temporal constraints during the peak e...

Full description

Saved in:
Bibliographic Details
Main Authors: Ikbal, S., Bourlard, H., Magimai-Doss, M.
Format: Conference Proceeding
Language:English
Subjects:
Acoustic noise
Autocorrelation
Frequency estimation
Hidden Markov models
Humans
Noise robustness
Spectrogram
Speech recognition
Time frequency analysis
Yield estimation
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we present an HMM/ANN based algorithm to estimate the spectral peak locations. This algorithm makes use of distinct time-frequency (TF) patterns in the spectrogram for estimating the peak locations. Such a use of TF patterns is expected to impose temporal constraints during the peak estimation task, thereby yielding a smoother estimate of the peaks over time. Additionally, the algorithm uses an ergodic topology for the HMM/ANN, thus allowing an estimation of a varying number of peak locations over time. The usefulness of the proposed algorithm is evaluated in the framework of a recently introduced noise robust feature called the spectro-temporal activity pattern (STAP) feature. Interestingly, the recently introduced phase autocorrelation (PAC) spectrum, with enhanced spectral peaks and smoothed spectral valleys, turns out to be more appropriate for this algorithm than the regular spectrum.
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.2005.1415148