Method for searching multimedia resource based on audio content retrieval

Abstract

The invention discloses a multimedia resource retrieval method based on audio content retrieval, comprising the following steps: 1) a pretreatment server converts video and audio into standard voice to be recognized; 2) a voice recognition server trains training corpus into an acoustical model, and matches the voice to be recognized with the acoustical model to obtain semantic text indexes; (3) an index server stores and recognizes keyword indexes, and matches the indexes with a retrieval condition to get a retrieval result. By using keyword retrieval technology in audio, the internal semantic information of audio / video resource can be obtained, the text type semantic information is indexed, therefore, the method provides more comprehensive and reliable audio / video resource information indexes, such that a retrieval system can get matched multimedia resource more accurately, and locate the precise position of retrieval keywords in audio / video.

Description

technical field [0001] The invention relates to a multimedia resource retrieval method based on audio content retrieval, in particular to a method for retrieving resources in the form of video and audio, finding the resource containing the retrieved information and giving the location of the retrieved information in the resource. Background technique [0002] In today's digital and network era, multimedia data has become the main part of the data transmitted on the Internet information highway. Multimedia content such as audio, images and video currently accounts for 15% of the Internet, and this number is still growing rapidly. The large-capacity and high-speed storage system provides a basic guarantee for the mass storage of audio and video, and the use of audio and video in various industries is becoming more and more extensive. How to obtain useful information from massive audio and video information, that is, the management and retrieval of audio and video information ...

AI Technical Summary

Problems solved by technology

[0006] Keyword recognition technology based on Hidden Markov Model is a very important aspect of speech retrieval. It occupies an important position in the specific content retrieval of speech. Due to the limitations of robustness and practicability of speech recognition technology, Using continuous speech recognition to build a large vocabulary, the recognizer of arbitrary keywords cannot achieve ideal results, and cannot well meet the application requirements of speech retrieval.

Images