1. Home
  2. Honda R&D Technical Review Vol.32 N...
  3. Experimental Environment for Verifi...

Technical Review e-Book: Summary

Experimental Environment for Verification of Speech-based News Delivery System

Article of Honda R&D Technical Review Vol.32 No.2

Summary

An original spoken dialogue system was developed that is capable of diverse responses to user utterances while communicating information using news articles distributed on the Internet. Most conventional spoken dialogue systems are question-and-answer types, and are not suited to communicating large amounts of information such as news articles. In addition, users are unable to interrupt news article read-aloud systems with questions. Therefore, new key technologies related to spoken dialogue systems were developed, including conversation summarization technology, a paralanguage recognizer, pause adjustment, and a speech synthesizer, and an experimental system was constructed that is capable of spoken dialogue in Japanese using news articles distributed in real time on the Internet. This enabled easy system verification in various usage scenarios. Practical application of this system will enable spoken dialogue in the manner of a conversation partner for drivers while driving.

Reference

(1) Takatsu, H., Fukuoka, I., Fujie, S., Hayashi, Y., Kobayashi, T.: A Spoken Dialogue System for Enabling Information Behavior of Various Intention Levels, Transactions of the Japanese Society for Artificial Intelligence, Vol. 33, No. 1, p. 1-24, (2018) (in Japanese)
(2) Takatsu, H., Honda, H., Fujie, S., Hayashi, Y., Kobayashi, T.: Kaiwa niyoru Nyusukiji Dentatsu notameno Yoyaku, NLP2019 proceedings, p. 518-521, (2019) (in Japanese)
(3) Gillick, D., Favre, B., Hakkani-Tür, D.: The ICSI Summarization System at TAC 2008, Text Analysis Conference (TAC) 2008, (2008)
(4) Takamura, H., Okumura, M.: Text Summarization Model based on Maximum Coverage Problem and its Variant, Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics, p. 781-789, (2009)
(5) Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding, Proceedings of NAACL-HLT 2019, p. 4171-4186, (2019)
(6) Lin, Z., Feng, M., dos Santos, C. N., Yu, M., Xiang, B., Zhou, B., Bengio, Y.: A Structured Self-attentive Sentence Embedding, Proceedings of the 5th International Conference on Learning Representations, p. 1-15, (2017)
(7) Takatsu, H., Yokoyama, K., Matsuyama, Y., Honda, H., Fujie, S., Kobayashi, T.: Recognition of Intentions of Users’ Short Responses for Conversational News Delivery System, Proceedings of the 20th Annual Conference of the International Speech Communication Association, p. 1193-1197, (2019)
(8) Yokoyama, K., Takatsu, H., Honda, H., Fujie, S., Kobayashi, T.: Investigation of Users' Short Responses in Actual Conversation System and Automatic Recognition of their Intentions, Proceedings of the 2018 IEEE Workshop on Spoken Language Technology, p. 934-940, (2018)
(9) Yokoyama, K., Takatsu, H., Honda, H., Fujie, S., Kobayashi, T.: Utterance Intention Classification and Recognition for Conversational News Delivery System, Information Processing Society of Japan SIG-SLP, Vol. 2018-SLP-123, No. 5, p. 1-8, (2018) (in Japanese)
(10) Takatsu, H., Yokoyama, K., Honda, H., Fujie, S., Hayashi, Y., Kobayashi, T.: Utterance Intention Understanding for News Articles Transfer by Conversation, JSAI2018 proceedings, 4Pin1-29, p. 1-4, (2018) (in Japanese)
(11) Yokoyama, K., Takatsu, H., Honda, H., Fujie, S., Hayashi, Y., Kobayashi, T.: Utterance Intention Classification and Database Construction for Conversational News Delivery System, JSAI2018 proceedings, 3Pin1-23, p. 1-4, (2018) (in Japanese)
(12) Takatsu, H., Yokoyama, K., Honda, H., Fujie, S., Hayashi, Y., Kobayashi, T.: Kaiwa niyoru Nyusukiji Dentatsu notameno Ma no Chosei, NLP2018 proceedings, p. 212-215, (2018) (in Japanese)
(13) Takatsu, H., Fukuoka, I., Fujie, S., Iwata, K., Kobayashi, T.: Speech Synthesis for Conversational News Contents Delivery, Transactions of the Japanese Society for Artificial Intelligence, Vol. 34, No. 2, p. 1-15, (2019) (in Japanese)
(14) Wu, Z., Swietojanski, P., Veaux, C., Renals, S., King, S.: A study of speaker adaptation for DNN-based speech synthesis, Proceedings of the 16th Annual Conference of the International Speech Communication Association, p. 879-883, (2015)

Author (organization or company)

Hiroshi HONDA(Honda Motor Co., Ltd.)、Hiroaki TAKATSU(Waseda University)、Yoichi MATSUYAMA(Waseda University)、Tetsunori KOBAYASHI(Waseda University)

We would like to get your opinion on this research paper. (This is only applicable to registered members.)

The readers of this research paper have also selected these research papers.

Analysis of Subjective Values of Car Users in Japan and U.S. Using Free Description Keyword Method
Article of Honda R&D Technical Review Vol.32 No.2
Guide Robot Management System
Article of Honda R&D Technical Review Vol.32 No.2
Modeling and Utilizing Expert’s Knowledge, Experience, and Thinking in Automobile Development
Article of Honda R&D Technical Review Vol.32 No.2