Microphone-array speech recognition via incremental map training

John E. Adcock, Yoshihiko Gotoh, Daniel J. Mashao, Harvey F. Silverman

Research output: Contribution to journalConference articlepeer-review

12 Citations (Scopus)


For a hidden Markov model (HMM) based speech recognition system it is desirable to combine enhancement of the acoustical signal and statistical representation of model parameters, ensuring both a high quality speech signal and an appropriately trained HMM. In this paper the incremental variant of maximum a posteriori (MAP) estimation is used to adjust the parameters of a talker-independent HMM-based speech recognition system to accurately recognize speech data acquired with a microphone-array. The approach is novel for a microphone-array speech recognition task in that a robust talker-independent model is derived from a baseline system using a relatively small amount of data for training. The results show that (1) MAP training significantly improves recognition performance compared to the baseline, and (2) beamforming signal enhancement out-performs single-channel enhancement before and after the adaptive MAP training.

Original languageEnglish
Pages (from-to)897-900
Number of pages4
JournalProceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing
Publication statusPublished - 1996
Externally publishedYes
EventProceedings of the 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP. Part 1 (of 6) - Atlanta, GA, USA
Duration: 7 May 199610 May 1996

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering


Dive into the research topics of 'Microphone-array speech recognition via incremental map training'. Together they form a unique fingerprint.

Cite this