Example-based query generation for spontaneous speech

IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01. - Trang 268-271
H. Murao1,2, N. Kawaguchi3,4, S. Matsubara5, Y. Inagaki6
1Center for Integrated Acoustic Information Research, University of Nagoya, Nagoya, Japan
2Hypermedia Research Center, Sanyo Electric Company Limited, Hirakata, Osaka, Japan
3Computation Center, University of Nagoya, Nagoya, Japan
4Nagoya Daigaku, Nagoya, Aichi, JP
5Center for Integrated Acoust. Inf. Res., Nagoya Univ., Japan
6Department of Computational Science and Engineering, University of Nagoya, Nagoya, Japan

Tóm tắt

This paper proposes a new query generation method that is based on examples of human-to-human dialogue. Along with modeling the information flow in dialogue, a system for information retrieval in-car has been designed. The system refers to the dialogue corpus to find an example that is similar to input speech, and makes a query from the example. We also give the experimental results to show the effectiveness of this method.

Từ khóa

#Speech #Information retrieval #Databases #Humans #Acoustical engineering #Natural languages #Robustness

Tài liệu tham khảo

10.1109/89.817450 10.1109/ICASSP.1996.540319 kawahara, 2000, Free software toolkit for japanese large vocabulary continuous speech recognition, Proc ICSLP 2000, 4, 476 kawaguchi, 2000, Construction of speech corpus in moving car environment, Proc ICSLP 2000, 3, 362 10.1109/ICSLP.1996.607775 10.1109/ICSLP.1996.607458
Thông tin
Thông tin xuất bản

IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01.

268-271

Thông tin tác giả