Indexing and search methods for spoken documents

被引：0

作者：

Burget, Lukas ^{[1
]}

Cernocky, Jan ^{[1
]}

Fapso, Michal ^{[1
]}

Karafiat, Martin ^{[1
]}

Matejka, Pavel ^{[1
]}

Schwarz, Petr ^{[1
]}

Smrz, Pavel ^{[1
]}

Szoke, Igor ^{[1
]}

机构：

[1] Brno Univ Technol, Speech FIT, Fac Informat Technol, Brno 61266, Czech Republic

来源：

TEXT, SPEECH AND DIALOGUE, PROCEEDINGS | 2006年 / 4188卷

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents two approaches to spoken document retrieval-search in LVCSR recognition lattices and in phoneme lattices. For the former one, an efficient method of indexing and search of multi-word queries is discussed. In phonetic search, the indexation of tri-phoneme sequences is investigated. The results in terms of response time to single and multi-word queries are evaluated on ICSI meeting database.

引用

页码：351 / 358

页数：8