Incorporating information from syllable-length time scales into automatic speech recognition

Su-Lin Wu, Brian Kingsbury, Nelson Morgan, Steven GreenbergICASSP 1998 · OpenReview

Abstract

Including information distributed over intervals of syllabic duration (100-250 ms) may greatly improve the performance of automatic speech recognition (ASR) systems. ASR systems primarily use representations and recognition units covering phonetic durations (40-100 ms). Humans certainly use information at phonetic time scales, but results from psychoacoustics and psycholinguistics highlight the crucial role of the syllable, and syllable-length intervals, in speech perception. We compare the performance of three ASR systems: a baseline system that uses phone-scale representations and units, an experimental system that uses a syllable-oriented front-end representation and syllabic units for recognition, and a third system that combines the phone-scale and syllable-scale recognizers by merging and rescoring N-best lists. Using the combined recognition system, we observed an improvement in word error rate for telephone-bandwidth, continuous numbers from 6.8% to 5.5% on a clean test set, and from 27.8% to 19.6% on a reverberant test set, over the baseline phone-based system.
BibTeX
@inproceedings{wu1998incorporating,
  author = {Su-Lin Wu and Brian Kingsbury and Nelson Morgan and Steven Greenberg},
  title = {{Incorporating information from syllable-length time scales into automatic speech recognition}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {1998},
  url = {https://openreview.net/forum?id=HFI3v-0CLe5},
}

Loading related content...

Figure