Speech retrieval method and system

Abstract

The invention provides speech retrieval method and system. The speech retrieval method comprises the steps of: receiving retrieval input from a user; extracting a plurality of retrieval input speech features and acquiring a first confidence degree of each retrieval input speech feature by utilizing multiple groups acoustic models and language models; respectively retrieving the plurality of retrieval input speech features to obtain a retrieval result list corresponding to each retrieval input speech feature as well as a second confidence degree and a search engine score recorded by each result record in the retrieval result list; calculating the retrieval score of each result record of each speech feature according to the first confidence degree, the second confidence degree and the search engine score of the voice feature and normalizing the retrieval scores; re-sequencing each retrieval result list according to the normalized retrieval score; and merging the resequenced retrieval result list of each feature to obtain a final retrieval list.

Description

technical field [0001] Embodiments of the present invention relate to a voice retrieval method and a voice retrieval system, and more specifically, relate to a voice retrieval method and a voice retrieval system that use multiple voice features for retrieval. Background technique [0002] In recent years, the traditional text retrieval has been increasingly unable to meet people's increasingly diverse needs. With the development of speech recognition technology, people pay more and more attention to speech retrieval based on speech recognition technology. However, since the user's pronunciation may be different from the predetermined standard pronunciation in the retrieval system during retrieval, in the current method of retrieval through a single speech feature (such as a word), the error rate of speech recognition is relatively high, and for There are high requirements for users to retrieve input pronunciations. [0003] A voice indexing and retrieval method is disclose...

AI Technical Summary

Problems solved by technology

[0005] However, in the existing voice retrieval methods, there are still problems such as low retrieval accuracy, and the results desired by users are not ranked in the relatively front position in the retrieval results.

In addition, when it is necessary to retrieve multiple languages ​​or new vocabulary, the existing speech retrieval methods need to rebuild the retrieval system, which means a huge workload

Images