Design of a speech recognition system based on acoustically derived segmental units

M. Bacchiani, M. Ostendorf, Yoshinori Sagisaka, K. Paliwal

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

The design of speech recognition system based on acoustically-derived, segmental units can be divided in three steps: unit design, lexicon building and pronunciation modeling. We formulate an iterative unit design procedure which consistently uses a maximum likelihood (ML) objective in successive application of resegmentation and model re-estimation. The lexicon building allows multi-word entries in the lexicon but restricts the number of these entries in order to avoid a too costly search. Selected multi-word lexical entries are those with high frequency (such as function words) and those which consistently exhibit cross-word phone assimilation. The stochastic pronunciation model represents the likelihood of a particular acoustic segment sequence given the phonetic baseform of a lexical item, where the sequence of baseform phones are treated as a Markov state sequence and each state can emit multiple segments.

Original languageEnglish
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
PublisherIEEE
Pages443-446
Number of pages4
Volume1
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: 1996 May 71996 May 10

Other

OtherProceedings of the 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP. Part 1 (of 6)
CityAtlanta, GA, USA
Period96/5/796/5/10

    Fingerprint

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Acoustics and Ultrasonics

Cite this

Bacchiani, M., Ostendorf, M., Sagisaka, Y., & Paliwal, K. (1996). Design of a speech recognition system based on acoustically derived segmental units. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (Vol. 1, pp. 443-446). IEEE.