Multilayer index voice document searching method and system thereof

Abstract

The invention discloses a multilayer indexing voice document retrieval method and a system thereof, and belongs to the technical field of information retrieval. The multilayer indexing voice document retrieval method comprises the following steps: (1) feature extraction of a multimedia stream is implemented, thus obtaining a voice feature sequence; (2) a voice identifying decoder is used for searching the voice feature sequences, thus obtaining a word lattice and an optimal identification result; (3) according to the word lattice and the optimal identification result, a word and syllable double-layer indexing database is constructed; and (4) relevant documents of a given query term are searched in the indexing database and returned to users. The multilayer indexing voice document retrieval system comprises an automatic voice identifying module that is used for automatically identifying characters in voice documents; an automatic voice document index constructing module that is used for constructing double indexes of the voice identification result, and a voice document retrieval module that is used for searching the relevant documents of given query terms in the indexing database and returning the documents to users. Compared with the prior art, the multilayer indexing voice document retrieval method and the system can realize quick and accurate searching of multimedia data.

Description

technical field [0001] The invention relates to a multi-layer index voice document retrieval method and system thereof, which uses voice information in multimedia materials for automatic cataloging and retrieval, belongs to the technical field of information retrieval, and can be applied to television stations, radio stations, and multimedia websites. Background technique [0002] With the rapid development of digital multimedia technology, the multimedia information faced by people is growing explosively. As the speed of the Internet continues to increase, more and more multimedia data exists on the Internet. At the same time, the construction of the digital library is becoming more and more perfect. Therefore, how to quickly and accurately obtain the required knowledge from massive multimedia data is an urgent problem to be solved. [0003] In recent years, information retrieval technology has become an important means for people to obtain information, and has profoundly...

AI Technical Summary

Problems solved by technology

[0006]In the current audio document retrieval system, most of the words are used as the index unit to construct the index, but there is a problem of out-of-set words when using the word to construct the index, so that when the search word The corresponding document cannot be found when it is an out-of-set word

Recently, some scholars have begun to study the construction of indexes based on sub-word units. Using sub-word units as index units will cause the problem that the returned documents are not accurate enough. This invention proposes a method of combining words and phonemes, so that the accuracy and recall performance of retrieval can be improved. good performance

Images