Nonlinear mapping for feature extraction in automatic speech recognition
AssigneeInternational Computer Science Institute
InventorsHynek Hermansky, Sangita Sharma, Daniel Ellis
Life of this patent
Estimating the term…
Abstract
The present invention successfully combines neural-net discriminative feature processing with Gaussian-mixture distribution modeling (GMM). By training one or more neural networks to generate subword probability posteriors, then using transformations of these estimates as the base features for a conventionally-trained Gaussian-mixture based system, substantial error rate reductions may be achieved. The present invention effectively has two acoustic models in tandem—first a neural net and then a GMM. By using a variety of combination schemes available for connectionist models, various systems based upon multiple features streams can be constructed with even greater error rate reductions.
Claims20
A method of combining neural-net discriminative feature processing with Gaussian-mixture distribution modeling in automatic speech recognition comprising:
- training at least one neural network to estimate a plurality of phone posterior probabilities from at least a portion of an audio stream containing speech;
- transforming the distribution of the plurality of posterior probabilities into a Gaussian distribution;
- de-correlating the transformed posterior probabilities;
- and
- applying the de-correlated and transformed posterior probabilities as features to a Gaussian mixture model automatic speech recognition system.
A computer program product, stored on a computer readable medium, comprising instructions operable to cause a programmable processor to:
- receive a plurality of subword posterior probabilities from at least one neural network trained to estimate subword posterior probabilities from at least a portion of an audio stream;
- transform a distribution of the plurality of posterior probabilities into a Gaussian distribution;
- de-correlate the transformed posterior probabilities;
- and
- supply the de-correlated and transformed posterior probabilities as features to a Gaussian mixture model speech recognition system.
A method of using neural-net discriminative feature processing with Gaussian-mixture distribution modeling for use in automatic speech recognition comprising:
- training a first plurality of neural networks to generate a set of pluralities of subword posterior probabilities from at least portions of an audio stream;
- non-linearly merging the set of pluralities of posterior probabilities into a merged plurality of posterior probabilities using a second neural network;
- transforming the distribution of the merged plurality of posterior probabilities into a Gaussian distribution;
- de-correlating the transformed merged plurality of posterior probabilities;
- and
- applying the de-correlated and transformed merged plurality of posterior probabilities as features to an automatic speech recognition system.
Dependencies are inferred from the claim text.