Speech recognition utilizing multitude of speech features

Abstract

In a speech recognition system, the combination of a log-linear model with a multitude of speech features is provided to recognize unknown speech utterances. The speech recognition system models the posterior probability of linguistic units relevant to speech recognition using a log-linear model. The posterior model captures the probability of the linguistic unit given the observed speech features and the parameters of the posterior model. The posterior model may be determined using the probability of the word sequence hypotheses given a multitude of speech features. Log-linear models are used with features derived from sparse or incomplete data. The speech features that are utilized may include asynchronous, overlapping, and statistically non-independent speech features. Not all features used in training need to appear in testing/recognition.

1 . A speech recognition system, comprising:
 a features extractor that extracts a multitude of speech features directly from input speech;   a log-linear function that receives the multitude of speech features obtained from the input speech and determines a posterior probability of each of a plurality of hypothesized linguistic units unit given the extracted multitude of speech features, and   a search device that analyzes the posterior probabilities determined by the log-linear function to determine a recognized output of unknown utterances.   
   
   
       2 . The speech recognition system of  claim 1 , wherein the log linear function models the posterior probability using a log linear model. 
   
   
       3 . The speech recognition system of  claim 1 , wherein the speech features comprise at least one of asynchronous, overlapping, and statistically non-independent speech features. 
   
   
       4 . The speech recognition system of  claim 1 , wherein at least one of the speech features extracted is derived from incomplete data. 
   
   
       5 . The speech recognition system of  claim 1 , further comprising a loopback. 
   
   
       6 . The speech recognition system of  claim 1 , wherein the features are extracted using direct matching between test data and training data. 
   
   
       7 . The speech recognition system of  claim 1 , wherein the features are extracted using Gaussian model identities at each time frame. 
   
   
       8 . A speech recognition method, comprising:
 extracting a multitude of speech features directly from input speech;   using a log linear function for determining a posterior probability of each of a plurality of hypothesized linguistic units given the extracted multitude of speech features, and   determining a recognized output of unknown utterances using the posterior probabilities.   
   
   
       9 . The speech recognition method of  claim 8 , wherein the log linear function models the posterior probability using a log linear model. 
   
   
       10 . The speech recognition method of  claim 8 , wherein the speech features comprise at least one of asynchronous, overlapping, and statistically non-independent speech features. 
   
   
       11 . The speech recognition method of  claim 8 , wherein at least one of the speech features extracted is derived from incomplete data. 
   
   
       12 . The speech recognition method of  claim 8 , further comprising a step of loopback. 
   
   
       13 . The speech recognition method of  claim 8 , wherein the features are extracted using direct matching between test data and training data. 
   
   
       14 . The speech recognition method of  claim 8 , wherein the extracting of a multitude of speech features comprises using Gaussian model identities at each time frame to identify and extract features. 
   
   
       15 . A program storage device storing a program of instructions executable by a machine for performing a method of speech recognition, the method comprising:
 extracting a multitude of speech features directly from input speech;   using a log linear function for determining a posterior probability of each of a plurality of hypothesized linguistic units given the extracted multitude of speech features, and   determining a recognized output of unknown utterances using the posterior probabilities.