Advanced Speech Technology Laboratory

 The Advanced Speech Technology Laboratory will realize practical speech recognition technologies in ten languages(Japanese, English, Chinese, Korean, Thai, Vietnamese, Indonesian, Myanmar, Spanish, and French) with the aim of implementing them in society for the 2020 Tokyo Olympics and Paralympics. Research and development involved includes (1) building speech corpora of about 2,000 hours in four languages, Japanese, English, Chinese and Korean, and of about 500 hours in the other languages; (2) developing multilingual and multidisciplinary language models; and( 3) developing high-speed, high-accuracy speech recognition engines. The Laboratory will also conduct research and development of speech synthesis technologies to realize practical speech synthesis systems in the above ten languages.

In terms of research and development for the world post-2020, the Laboratory will aim to realize technologies for the conversion of all speech contents around the globe into text. It will conduct research and development of technologies for recognizing speech generated by multiple people speaking different languages in environments such as public spaces with background noise and echoing, and technologies for mixed-language dialogue in many languages.