Presentation | 2005/12/15 Speech interface for organization name input based on combination of isolated word recognition and continuous base-word recognition Norihide KITAOKA, Hironori OSHIKAWA, Seiichi NAKAGAWA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this report, we propose a multimodal interface for organization name input based on combinational usage of isolated word recognition for high frequency names and base-word recognition for low frequency names. Using this interface, the user first utters a organization name and then the system displays multiple word hypotheses and base-word lattice. Then the user selects a word or base-words to construct the name he/she intends to input. There are a huge number of organization names and new names are continuously generated, so the system cannot prepare all the names a priori. We addressed this problem to obtain both high coverage and high recognition performance by combining isolated word recognition and continuous base-word recognition. We proposed a multimodal interface to select a whole word or base-words to construct the word the user wanted to input by touch pen. We evaluated this combinational recognition method by off-line experiment and obtained the result better than both isolated word recognition only and continuous base-word recognition only. The simulation result of the system was about 92%. We also evaluated the performance of on-line system and revealed that the user can input a word by 93.3% by at most two trials of the utterances despite the recognition performance degradation. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | organization name input / speech recognition / isolated word recognition / continuous base-word recognition |
Paper # | NLC2005-77,SP2005-110 |
Date of Issue |
Conference Information | |
Committee | NLC |
---|---|
Conference Date | 2005/12/15(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Natural Language Understanding and Models of Communication (NLC) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Speech interface for organization name input based on combination of isolated word recognition and continuous base-word recognition |
Sub Title (in English) | |
Keyword(1) | organization name input |
Keyword(2) | speech recognition |
Keyword(3) | isolated word recognition |
Keyword(4) | continuous base-word recognition |
1st Author's Name | Norihide KITAOKA |
1st Author's Affiliation | Department of Information and Computer Sciences, Toyohashi University of Technology() |
2nd Author's Name | Hironori OSHIKAWA |
2nd Author's Affiliation | Department of Information and Computer Sciences, Toyohashi University of Technology |
3rd Author's Name | Seiichi NAKAGAWA |
3rd Author's Affiliation | Department of Information and Computer Sciences, Toyohashi University of Technology |
Date | 2005/12/15 |
Paper # | NLC2005-77,SP2005-110 |
Volume (vol) | vol.105 |
Number (no) | 494 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |