The modulation spectrum in the automatic recognition of speech

Author

Hermansky, Hynek

Author_Institution

Dept. of Electr. & Comput. Eng., Graduate Inst. of Sci. & Technol., Portland, OR, USA

fYear

1997

fDate

14-17 Dec 1997

Firstpage

140

Lastpage

147

Abstract

The article questions the reliability of the short term spectral envelope as the dominant carrier of the phonetic identity of a given speech instant and suggests the temporal dynamics of components of the spectral envelopes as more reliable means for deriving the linguistic context of the speech message. It shows that analysis of the modulation spectrum offers a means for the systematic evaluation of medium term temporal dynamics of speech features. Such a medium term dynamic has been previously efficiently utilized in the computation of dynamic features and in RASTA processing. We aim for data driven analysis of the modulation spectrum and demonstrate the importance of syllabic rate modulation spectral components for speech communication

Keywords

modulation spectra; speech processing; speech recognition; temporal logic; RASTA processing; automatic speech recognition; data driven analysis; linguistic context; medium term dynamic; medium term temporal dynamics; modulation spectrum; phonetic identity; short term spectral envelope; speech communication; speech features; speech instant; speech message; syllabic rate modulation spectral components; systematic evaluation; temporal dynamics; Additive noise; Auditory system; Automatic speech recognition; Frequency modulation; Humans; Spectral analysis; Speech analysis; Speech coding; Speech enhancement; Speech processing;

fLanguage

English

Publisher

ieee

Conference_Titel

Automatic Speech Recognition and Understanding, 1997. Proceedings., 1997 IEEE Workshop on

Conference_Location

Santa Barbara, CA

Print_ISBN

0-7803-3698-4

Type

conf

DOI

10.1109/ASRU.1997.658998

Filename

658998