Cross-lingual Speaker Adaptation via Gaussian Component Mapping
Refereed conference paper presented and published in conference proceedings

Full Text

Times Cited
Web of Science1WOS source URL (as at 11/10/2021) Click here for the latest count

Other information
AbstractThis paper is focused on the use of acoustic information from an existing source language (Cantonese) to implement speaker adaptation for a new target language (English). Speaker-independent (SI) model mapping between Cantonese and English is investigated at different levels of acoustic units. Phones, states, and Gaussian mixture components are used as the mapping units respectively. With the model mapping, cross-lingual speaker adaptation can be performed. The performance of the proposed cross-lingual speaker adaptation system is determined by model mapping effectiveness and speaker adaptation effectiveness. Experimental results show that the model mapping effectiveness increased with the refinement of mapping units, and the speaker adaptation effectiveness depends on the model mapping effectiveness. Mapping between Gaussian mixture components is proved effective for various speech recognition tasks. A relative error reduction of 10.12% on English words is achieved by using a small amount of (4 minutes) Cantonese adaptation data, compared with the SI English recognizer.
All Author(s) ListCao HW, Lee T, Ching PC
Name of Conference11th Annual Conference of the International-Speech-Communication-Association 2010
Start Date of Conference26/09/2010
End Date of Conference30/09/2010
Place of ConferenceMakuhari
Country/Region of ConferenceJapan
Detailed descriptionorganized by International Speech Communication Association,
Pages869 - 872
LanguagesEnglish-United Kingdom
Keywordscross-lingual; model mapping; speaker adaptation; speech recognition
Web of Science Subject CategoriesComputer Science; Computer Science, Artificial Intelligence; Engineering; Engineering, Electrical & Electronic

Last updated on 2021-12-10 at 00:07