Speech-Activated Text Retrieval System for Cellular Phones with Web Browsing Capability

Proceedings of PACLIC 19, the 19th Asia-Pacific Conference on Language, Information and Computation. Speech-Activated Text Retrieval System for Cellular Phones with Web Browsing Capability Takahiro Ikeda Shin-ya Ishikawa Kiyokazu Miki Fumihiro Adachi Ryosuke Isotani Kenji Satoh Akitoshi Okumura Media and Information Research Laboratories, NEC Corporation 1753 Shimonumabe, Nakahara-Ku, Kawasaki, Kanagawa 211-8666, Japan t-ikeda@di.jp.nec.com s-ishikawa@dg.jp.ne.com k-miki@bq.jp.nec.com f-adachi@aj.jp.nec.com r-isotani@bp.jp.nec.com k-satoh@da.jp.nec.com a-okumura@bx.jp.nec.com Abstract This paper describes a text retrieval system for cellular phones with Web browsing capability, which accepts spoken queries over the cellular phone and provides the search result on the cellular phone screen. This system recognizes spoken queries by large vocabulary continuous speech recognition (LVCSR), retrieves relevant document by text retrieval, and provides the search result on the World Wide Web by the integration of the Web and the voice systems. The text retrieval in this system improves the performance for spoken short queries by: 1) utilizing word pairs with dependency relations, 2) distinguishing affirmative and negative expressions, and 3) converging synonyms. The LVCSR in this system shows enough performance level for speech over the cellular phone with acoustic and language models derived from a query corpus with target contents. The system constructed for user’s manual for a cellular phone navigates users to relevant passages for 81.4% of spoken queries. 1. Introduction Cellular phones are now widely used and those with Web browsing capability are becoming very popular. Users can easily browse information provided on the World Wide Web such as news, weather, and traffic report with the cellular phone screen in mobile environment. However, obtaining necessary information from large database such as user’s manual or travelers’ guide is quite a task for users since searching for appropriate information from seas of data requires cumbersome key operations. In most cases, users have to carefully navigate through deep hierarchical structures of menus or have to type in complex combination of keys to enter some keywords. Text retrieval by voice input is one of the solutions for this problem. This paper presents a telephone-based voice query retrieval system in Japanese which enables cellular phone users to search through the user’s manual. This system accepts spoken queries over the cellular phone with large vocabulary continuous speech recognition (LVCSR) and retrieves relevant parts from the user’s manual with text retrieval. The results are provided to the user as a Web page by synchronously activating the Web and the voice systems (Yoshida et al., 2002). Users can input queries without complicated keystrokes and can view the list of results on the cellular phone screen. With respect to voice input systems, a large number of interactive voice responses (IVR) systems and spoken dialogue systems has been designed and developed over the years (Zue, 1997). As for user’s manual retrieval systems which accept voice input, Kawahara et al. (2003) has developed a spoken dialogue system for appliance manuals. However, they mainly focus on the dialogue strategy to select the appropriate result on screen-less systems such as VTR and FAX. On the other hand, retrieval methods for voice input …

Content truncated to 500 words