This research presents a new approach for blind channel estimation for audio signals. For most speech processing techniques such as speech recognition or speaker identification, the performance can drop significantly when the statistics of the training data such as the channel shape, noise, and distortion differ from the statistics of the testing data. Aside from the standard technique of cepstral mean normalization, few techniques are available for reducing channel mismatch conditions. Experimental results will be presented for both channel estimation and for channel normalization via inverse filtering where the inverse filter is derived from the channel estimate.
Blind channel estimation for audio signals
2004 IEEE Aerospace Conference Proceedings (IEEE Cat. No.04TH8720) ; 5 ; 3144-3150 Vol.5
2004-01-01
481636 byte
Conference paper
Electronic Resource
English
10.0401 Blind Channel Estimation for Audio Signals
British Library Conference Proceedings | 2004
|Audio guidance system for blind
IEEE | 2017
|Blind Symbol Estimation Method in Frequency Selective Fading Channel
British Library Online Contents | 2000
|Locating apparatuses by means of audio signals using a deterministic data channel
European Patent Office | 2015
|