A system and method for effectively implementing an optimized language model for speech recognition includes initial language models each created by combining source models according to selectable interpolation coefficients that define proportional relationships for combining the source models. A rescoring module iteratively utilizes the initial language models to process input development data for calculating word-error rates that each correspond to a different one of the initial language model...

The present invention relates to a voice recognition apparatus capable of easily registering a word which has not been registered. The registering of an unregistered word into a dictionary can be easily performed without causing a significant increase in the size of the dictionary. The clustering unit detects a cluster (detected cluster) to which a new unregistered word is to be added as a new member, from existing clusters obtained by clustering unregistered words. The unregistered word is adde...

A method and apparatus are provided that generate values for a first set of dimensions of a feature vector from a speech signal. The values of the first set of dimensions are used to estimate values for a second set of dimensions of the feature vector to form an extended feature vector. The extended feature vector is then used to train an acoustic model.

In large-scale deployments of speaker recognition systems the potential for legacy problems increases as the evolving technology may require configuration changes in the system thus invalidating already existing user voice accounts. Unless the entire database of original speech waveform were stored, users need to reenroll to keep their accounts functional, which, however, may be expensive and commercially not acceptable. Model migration is defined as a conversion of obsolete models to new-config...

The present method incorporates audio and visual cues from human gesticulation for automatic recognition. The methodology articulates a framework for co-analyzing gestures and prosodic elements of a person's speech. The methodology can be applied to a wide range of algorithms involving analysis of gesticulating individuals. The examples of interactive technology applications can range from information kiosks to personal computers. The video analysis of human activity provides a basis for the dev...

A method and apparatus to perform voice detection are described.

Each word to be recognized is represented by gender-specific hidden Markov models that are stored in a ROM 6 along with output probability functions and preset transition probabilities. A speech recognizer 4 determines an occurrence probability of a feature parameter sequence detected by a feature value detector 3 using the hidden Markov models. The speech recognizer 4 determines the occurrence probability by giving each word a state sequence of one hidden Markov model common to the gender-speci...

Before executing a speech recognition, a composite acoustic model adapted to noise is generated by composition of a noise adaptive representative acoustic model generated by noise-adaptation of each representative acoustic model and difference models stored in advance in a storing section, respectively. Then, the noise and speaker adaptive acoustic model is generated by executing speaker-adaptation to the composite acoustic model with the feature vector series of uttered speech. The renewal diff...

A standard model creating apparatus which provides a high-precision standard model used for pattern recognition such as speech recognition, character recognition, or image recognition using a probability model based on a hidden Markov model, Bayesian theory, or linear discrimination analysis; intention interpretation using a probability model such as a Bayesian net; data-mining performed using a probability model; and so forth. The standard model creating apparatus includes a reference model pre...

In some embodiments, the invention includes calculating estimated weights for identified errors in recognition of utterances. Sections of the utterances are marked as being misrecognized and the corresponding estimated weights are associated with these sections of the utterances. The weighted sections of the utterances are used to convert a speaker independent model to a speaker dependent model.