内容紹介

More than 6800 living languages are spoken in the world today, one third are found in Asia. As globalization rapidly expands, multilingual speech recognition that can automatically recognize human spoken languages, become increasingly important. However, as every language has its own specific acoustic as well as linguistic, technologies developed based on models of one language cannot simply be ported “as-is” to other languages. In this talk, I will briefly describe the fundamental approach of automatic speech recognition, and discuss what the challenges in developing ASR systems for Asian languages. Finally, I will discuss what kind of special modeling techniques that can be applied to solve the problems.

詳細情報

刊年

2012

形態

電子化映像資料(30分2秒)

シリーズ名

情報科学研究科・ゼミナール講演 ; 平成24年度

注記

奈良先端科学技術大学院大学 情報科学研究科 知能コミュニケーション研究室

講演日: 平成24年4月25日

講演場所: 情報科学研究科大講義室L1

標題言語

英語 (eng)

本文言語

英語 (eng)

著者情報

Watiasri, Sakti Sakriani