Speech recognition optimizing system aiming at locale language use preference and method thereof

Abstract

The invention provides a speech recognition optimization system aiming at the using preference of regional languages, which comprises a lexicon establishment and classification module, a grammar model initialization module, a lexical database, a grammar weight calculation and grammar model generation module, a lexicon application recording module and a telephone speech recognition system. The lexicon establishment and classification module, the grammar model initialization module, the lexical database, the grammar weight calculation and grammar model generation module and the lexicon application recording module are arranged in a computer; the lexicon establishment and classification module, the grammar model initialization module, the telephone speech recognition system, the lexicon application recording module, the lexical database, the grammar weight calculation and grammar model generation module are connected in sequence and the telephone speech recognition system is connected with a speech input and output device through PSTN or the Internet. The system of the invention can effectively break through the bottle neck of algorithm optimization and is more suitable for the requirements of the application of industry.

Description

technical field [0001] The telephone speech recognition technology of the present invention specifically refers to a speech recognition optimization system and method for regional language usage preferences. Background technique [0002] Speech recognition technology has made tremendous progress in recent years. Currently the world's most advanced telephone speech recognition system - Nuance8.5 has achieved a recognition rate of about 95% for isolated words (Isolate Words) with small and medium vocabularies. A recognition rate of 95% is only a qualified standard in terms of satisfying users. From the perspective of product user experience and service quality, the speech recognition system may be required to have a more accurate recognition effect. In this way, the optimization of the speech recognition system to effectively improve the recognition rate of the speech recognition system has also become a major subject of many scientific researchers and speech recognition engi...

AI Technical Summary

Problems solved by technology

[0003] The optimization of speech recognition in the industry often focuses only on the improvement of the recognition algorithm. However, this method of recognition optimization still has certain limitations. When it comes to complex algorithms, the CPU usage is high, the calculation time is long, and the dependence on hardware devices is too large

In view of this, the algorithm-improved speech recognition optimization scheme has high cost and low benefit in actual industry applications

Images