ISCA Archive Interspeech 2008
ISCA Archive Interspeech 2008

Seed models combination and state level mappings of cross-lingual transfer for rapid HMM development: from English to Mandarin

Xufang Zhao, Douglas O'Shaughnessy

The practice of cross-lingual transfer of speech technology is of increasing concern as the demand for recognition systems in multiple languages grows. Previous work has proved that: firstly, if there is a big difference between the source language and the target language, cross-lingual adaptation may not outperform scratch training even if the training set is limited; secondly, cross-lingual seed models achieve lower word error rates than flat starts or random models. Based on these two points, this paper improved the approach of generating cross-lingual seed models through two ways: (1) using a combination of cross-lingual seed models and "flat-start" models, and (2) using phoneme mappings on an HMM state level in a new language to reduce mismatched coarticulation. All simulations are carried out with limited available training data, and the effectiveness of the approach was proved using English-Mandarin as a test case.


doi: 10.21437/Interspeech.2008-669

Cite as: Zhao, X., O'Shaughnessy, D. (2008) Seed models combination and state level mappings of cross-lingual transfer for rapid HMM development: from English to Mandarin. Proc. Interspeech 2008, 2699-2702, doi: 10.21437/Interspeech.2008-669

@inproceedings{zhao08c_interspeech,
  author={Xufang Zhao and Douglas O'Shaughnessy},
  title={{Seed models combination and state level mappings of cross-lingual transfer for rapid HMM development: from English to Mandarin}},
  year=2008,
  booktitle={Proc. Interspeech 2008},
  pages={2699--2702},
  doi={10.21437/Interspeech.2008-669}
}