An efficient phonotactic-acoustic system for language identification

Jirí Navrátil, Werner ZühlkeICASSP 1998 · OpenReview

Abstract

This paper presents a combined two-component system for language identification based on phonotactic and acoustic features. The phonotactic part consisting of a multilingual phone-recognizer with a double bigram-decoding architecture and a phonetic-context mapping is supported by a second part with pronunciation modeling of the recognized phone-sequence using Gaussian density models. Both parts are post-processed by a neural-based final classifier. Measured on the NIST'95 evaluation set, the described system outperforms state-of-the-art components and, at the same time, requires considerably less computational expense, as compared to implicit phonotactic-acoustic modeling and parallel recognizer architectures.
BibTeX
@inproceedings{navratil1998efficient,
  author = {Jirí Navrátil and Werner Zühlke},
  title = {{An efficient phonotactic-acoustic system for language identification}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {1998},
  url = {https://openreview.net/forum?id=vIarSwDBjcB},
}

Loading related content...

Figure