ISCA Archive Eurospeech 1997
ISCA Archive Eurospeech 1997

On the importance of various modulation frequencies for speech recognition

Noboru Kanedera, Takayuki Arai, Hynek Hermansky, Misha Pavel

Temporal processing of the time trajectories in the logarithmic spectrum domain, performed in cepstral mean subtraction, in computation of dynamic features in speech, or in RASTA processing, is becoming a common procedure in current ASR. Such temporal processing effectively enhances some components of the modulation spectrum of speech while suppressing others. It is therefore important to know the relative importance of various components of the modulation spectrum of speech. In this study we report on the effect of band-pass filtering of the time trajectories of spectral envelopes on speech recognition. Results indicate the relative importance of different components of the modulation spectrum of speech for ASR.


doi: 10.21437/Eurospeech.1997-104

Cite as: Kanedera, N., Arai, T., Hermansky, H., Pavel, M. (1997) On the importance of various modulation frequencies for speech recognition. Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997), 1079-1082, doi: 10.21437/Eurospeech.1997-104

@inproceedings{kanedera97_eurospeech,
  author={Noboru Kanedera and Takayuki Arai and Hynek Hermansky and Misha Pavel},
  title={{On the importance of various modulation frequencies for speech recognition}},
  year=1997,
  booktitle={Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997)},
  pages={1079--1082},
  doi={10.21437/Eurospeech.1997-104},
  issn={1018-4074}
}