Speech recognition system and method with cepstral noise subtraction
AssigneeIndustrial Technology Research Institute
InventorShih-Ming Huang
Life of this patent
Estimating the term…
Abstract
The invention relates to a speech recognition system and method with cepstral noise subtraction. The speech recognition system and method utilize a first scalar coefficient, a second scalar coefficient, and a determining condition to limit the process for the cepstral feature vector, so as to avoid excessive enhancement or subtraction in the cepstral feature vector, so that the operation of the cepstral feature vector is performed properly to improve the anti-noise ability in speech recognition. Furthermore, the speech recognition system and method can be applied in any environment, and have a low complexity and can be easily integrated into other systems, so as to provide the user with a more reliable and stable speech recognition result.
Claims18
A speech recognition system with cepstral noise subtraction, comprising:
- a filterbank energy extractor, for obtaining a plurality of first feature vectors according to a voice signal;
- a cepstral noise subtraction device, for obtaining a first feature vector of a preset voice frame and first feature vectors of a plurality of voice frames before the preset voice frame, so as to calculate a feature mean vector, and calculate a second feature vector of a preset voice frame according to the first feature vector, the feature mean vector, a first scalar coefficient, and a second scalar coefficient of the preset voice frame;
- a cepstral converter, for converting the second feature vector of the preset voice frame into a cepstral feature vector;
- a model trainer, for calculating a model parameter according to the cepstral feature vector;
- and
- a speech recognizer, for calculating a recognized voice signal according to the cepstral feature vector and the model parameter.
A speech recognition method with cepstral noise subtraction, comprising:
- obtaining a plurality of first feature vectors according to a voice signal;
- obtaining a first feature vector of a preset voice frame and first feature vectors of a plurality of voice frames before the preset voice frame, so as to calculate a feature mean vector;
- calculating a second feature vector of a preset voice frame according to the first feature vector, the feature mean vector, a first scalar coefficient, and a second scalar coefficient of the preset voice frame;
- converting the second feature vector of the preset voice frame into a cepstral feature vector;
- calculating a model parameter according to the cepstral feature vector;
- and
- calculating a recognized voice signal according to the cepstral feature vector and the model parameter.
Dependencies are inferred from the claim text.