Method and system for radio and television speech recognition system

Abstract

The invention discloses a broadcast television voice recognition method and system. The method comprises the following steps: extracting audio data according to broadcast television data; pre-processing the audio data to obtain feature text data; transmitting the feature text data to a cloud server for recognition to achieve male and female voice recognition, speaker recognition and voice recognition results; fusing the male and female voice recognition, speaker recognition and voice recognition results and marking a structured text to generate a structured voice recognition result. According to the method, the conventional voice recognition method is improved; various broadcast television data pre-processing technologies and broadcast television voice recognition methods are integrated; voice data is identified to meet data processing requirements in broadcast television industry; various recognition results are integrated to generate the structured voice recognition result; basic data can be provided for intelligent processing of other service of subsequent broadcast television programs; processing speed is increased; the accuracy is improved.

Description

technical field [0001] The invention relates to the technical field of audio and video processing, in particular to a radio and television voice recognition method and system. Background technique [0002] At present, in the field of radio and television, traditional speech recognition methods suitable for various industries are mainly used for radio and television speech recognition, and traditional speech recognition mainly uses pattern matching method, which is divided into two stages: training and recognition. In the training stage, the user will Each word in the vocabulary is read or spoken in turn, and its feature vector is stored as a template in the template library; in the recognition stage, the feature vector of the input speech is compared with each template in the template library in turn, and the The one with the highest similarity is output as the recognition result. [0003] But the voice recognition of this voice recognition application has the following pro...

AI Technical Summary

Problems solved by technology

[0004] 1) The radio and television industry often has special processing and operations for speech recognition that are different from other industries. However, because the above-mentioned traditional speech recognition is applied to various industries, it is not targeted for the radio and television industry, and cannot be based on the characteristics of the radio and television industry. Filtering of non-speech content in broadcast TV data

Because non-speech content is not within the scope of processing for speech recognition in the radio and television industry, if non-speech content is not filtered, it needs to be transmitted and processed, which not only leads to waste of transmission resources and computing resources, but also It will also cause more misrecognition operations due to the existence of non-speech content, and affect the processing speed

[0005] 2) Because the traditional voice recognition technology does not have the voice recognition function for the radio and television industry, the recognition results are not complete. The content is segmented according to different speakers, and the time stamp of each voice word cannot be identified, and it cannot provide any valuable reference information for the subsequent intelligent and automatic processing of other broadcast and television services

[0006] In summary, the application of traditional speech recognition methods in the broadcasting and television industry has problems such as resource consumption, slow processing speed, low accuracy, and insufficient information provided.

Images