Generalized optimization algorithm for speech recognition transducers

Cyril Allauzen, Mehryar Mohri

Research output: Contribution to journalConference articlepeer-review


Weighted transducers provide a common representation for the components of a speech recognition system. In previous work, we showed that these components can be combined off-line into a single compact recognition transducer that maps directly HMM state sequences to word sequences. The construction of that recognition transducer and its efficiency of use critically depend on the use of a general optimization algorithm, determinization. However, not all weighted automata and transducers used in large-vocabulary speech recognition are determinizable. We present a general algorithm that can make an arbitrary weighted transducer determinizable and generalize our previous optimization technique for building an integrated recognition transducer to deal with arbitrary weighted transducers used in speech recognition. We report experimental results in a large-vocabulary speech recognition task, How May I Help You (HMIHY), showing that our generalized technique leads to a recognition transducer that performs as well as our original solution in the case of classical n-gram models while inserting less special symbols, and that it leads to a substantial improvement of the recognition speed, factor of 2.6, in the same task when using a class-based language model.

Original languageEnglish (US)
Pages (from-to)352-355
Number of pages4
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
StatePublished - 2003
Event2003 IEEE International Conference on Accoustics, Speech, and Signal Processing - Hong Kong, Hong Kong
Duration: Apr 6 2003Apr 10 2003

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering


Dive into the research topics of 'Generalized optimization algorithm for speech recognition transducers'. Together they form a unique fingerprint.

Cite this