Title :
Speech-recognizer-based filter optimization for microphone array processing
Author :
Seltzer, Michael L. ; Raj, Bhiksha
Author_Institution :
Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA
fDate :
3/1/2003 12:00:00 AM
Abstract :
Conventional microphone array processing schemes used for speech recognition enhance the output waveform using optimization criteria that are independent of the recognition system. We present a new filter-and-sum array processing algorithm in which the filter parameters are calibrated to maximize recognizer likelihoods. The proposed method provides significant improvement in recognition accuracy over conventional methods.
Keywords :
acoustic signal processing; acoustic transducer arrays; array signal processing; calibration; filtering theory; hidden Markov models; microphones; optimisation; speech processing; speech recognition; HMM; filter parameters; filter-and-sum array processing algorithm; hidden Markov model; microphone array processing; microphone array processing calibration algorithm; optimization criteria; output waveform; recognition accuracy; recognizer likelihoods maximization; speech recognizer based filter optimization; Array signal processing; Calibration; Delay; Digital filters; Finite impulse response filter; Hidden Markov models; Microphones; Signal processing; Signal processing algorithms; Speech recognition;
Journal_Title :
Signal Processing Letters, IEEE
DOI :
10.1109/LSP.2002.807877
