ISCA Archive Interspeech 2008
ISCA Archive Interspeech 2008

Target-oriented phone selection from universal phone set for spoken language recognition

Rong Tong, Bin Ma, Haizhou Li, Eng Siong Chng

This paper studies target-oriented phone selection strategy for constructing phone tokenizers in the Parallel Phone Recognizers followed by Vector Space Model (PPR-VSM) paradigm of spoken language recognition. With this phone selection strategy, one derives a set of target-oriented phone tokenizers (TOPT), each having a subset of phones that have high discriminative ability for a target language. Two phone selection methods are proposed to derive such phone subsets from a phone recognizer. We show that the TOPTs derived from a universal phone recognizer (UPR) outperform those derived from language specific phone recognizers. The TOPT front-end derived from a UPR also consistently outperforms the UPR front-end without involving additional acoustic modeling. We achieve an equal error rates (EERs) of 1.33%, 1.75% and 2.80% on NIST 1996, 2003 and 2007 LRE databases respectively for 30 second closed-set tests by including multiple TOPTs in the PPR.


doi: 10.21437/Interspeech.2008-224

Cite as: Tong, R., Ma, B., Li, H., Chng, E.S. (2008) Target-oriented phone selection from universal phone set for spoken language recognition. Proc. Interspeech 2008, 715-718, doi: 10.21437/Interspeech.2008-224

@inproceedings{tong08_interspeech,
  author={Rong Tong and Bin Ma and Haizhou Li and Eng Siong Chng},
  title={{Target-oriented phone selection from universal phone set for spoken language recognition}},
  year=2008,
  booktitle={Proc. Interspeech 2008},
  pages={715--718},
  doi={10.21437/Interspeech.2008-224}
}