Title :
Sub-band based recognition of noisy speech
Author :
Tibrewala, Sangita ; Hermansky, Hynek
Author_Institution :
Oregon Graduate Inst. of Sci. & Technol., Beaverton, OR, USA
Abstract :
A new approach to automatic speech recognition based on independent class-conditional probability estimates in several frequency sub-bands is presented. The approach is shown to be especially applicable to environments which cause partial corruption of the frequency spectrum of the signal. Some of the issues involved in the implementation of the approach are also addressed
Keywords :
acoustic noise; estimation theory; probability; spectral analysis; speech recognition; automatic speech recognition; frequency spectrum; frequency sub-bands; independent class-conditional probability estimates; noisy speech; partial corruption; sub-band based recognition; Automatic speech recognition; Decoding; Degradation; Frequency estimation; Humans; Merging; Power system modeling; Speech enhancement; Speech recognition; Vocabulary;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1997. ICASSP-97., 1997 IEEE International Conference on
Conference_Location :
Munich
Print_ISBN :
0-8186-7919-0
DOI :
10.1109/ICASSP.1997.596173
