Improving speech recognition performance by using multi-model approaches

Ji Ming*, Philip Hanna, Darryl Stewart, Marie Owens, F. Jack Smith

*Corresponding author for this work

Research output: Contribution to conferencePaper

9 Citations (Scopus)

Abstract

Most current speech recognition systems are built upon a single type of model, e.g. an HMM or certain type of segment based model, and furthermore typically employs only one type of acoustic feature e.g. MFCCs and their variants. This entails that the system may not be robust should the modeling assumptions be violated. Recent research efforts have investigated the use of multi-scale/multi-band acoustic features for robust speech recognition. This paper described a multi-model approach as an alternative and complement to the multi-feature approaches. The multi-model approach seeks a combination of different types of acoustic model, thereby integrating the capabilities of each individual model for capturing discriminative information. An example system built upon the combination of the standard HMM technique with a segment-based modeling technique was implemented. Experiments for both isolated-word and continuous speech recognition have shown improved performances over each of the individual models considered in isolation.

Original languageEnglish
Pages161-164
Number of pages4
Publication statusPublished - 01 Jan 1999
EventProceedings of the 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-99) - Phoenix, United States
Duration: 15 Mar 199919 Mar 1999

Conference

ConferenceProceedings of the 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-99)
CountryUnited States
CityPhoenix
Period15/03/199919/03/1999

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Improving speech recognition performance by using multi-model approaches'. Together they form a unique fingerprint.

  • Cite this

    Ming, J., Hanna, P., Stewart, D., Owens, M., & Smith, F. J. (1999). Improving speech recognition performance by using multi-model approaches. 161-164. Paper presented at Proceedings of the 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-99), Phoenix, United States.