ISCA Archive ICSLP 1994
ISCA Archive ICSLP 1994

Phone-based prefiltering for continuous speech recognition

Renato De Mori, Diego Giuliani, Roberto Gretter

An architecture for speech recognition is proposed, based on four stages: (1) recognition of the most likely phone sequence using centisecond Hidden Markov Models (HMMs); (2) phone-based lexical and syntactical forward decoding; (3) A*phone-based backward pass, producing a Word Hypothesis Structure (WHS); (4) accurate rescoring of the search sub-space represented by the WHS using centisecond HMMs. Experiments carried out on two different tasks show that a recognizer based on the proposed four-stage architecture is able to achieve comparable performance respect to a classic one-stage recognizer. Experimental results show also that the same recognition performance can be obtained with WHSs built with this approach and WHSs built using centisecond HMMs with a potential speed-up, in WHS generation, proportional to the average phoneme duration in centiseconds.


Cite as: Mori, R.D., Giuliani, D., Gretter, R. (1994) Phone-based prefiltering for continuous speech recognition. Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994), 2203-2206

@inproceedings{mori94_icslp,
  author={Renato De Mori and Diego Giuliani and Roberto Gretter},
  title={{Phone-based prefiltering for continuous speech recognition}},
  year=1994,
  booktitle={Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994)},
  pages={2203--2206}
}