International Business Machines Corporation

Nuance Communications, Inc.

Sabine V Deligne

Ramesh Ambat Gopinath

Vaibhava Goel

Yuqing Gao

Hong-Kwang Jeff Kuo

Cheng Wu

Chalapathy Venkata Neti

Lidia Mangu

Gerasimos Potamianos

Satyanarayana Dharanipragada

Dimitri Kanevsky

Mahesh Viswanathan

Nagendra Kumar Goel

Benoit Emmanuel Ghislain Maison

The present invention concerns methods and apparatus for identifying and assigning meaning to words not recognized by a vocabulary or grammar of a speech recognition system. In an embodiment of the invention, the word may be in an acoustic vocabulary of the speech recognition system, but may be unrecognized by an embedded grammar of a language model of the speech recognition system. In another embodiment of the invention, the word may not be recognized by any vocabulary associated with the speech recognition system. In embodiments of the invention, at least one hypothesis is generated for an utterance not recognized by the speech recognition system. If the at least one hypothesis meets at least one predetermined criterion, a sword or more corresponding to the at least one hypothesis is added to the vocabulary of the speech recognition system. In other embodiments of the invention, before adding the word to the vocabulary of the speech recognition system, the at least one hypothesis may be presented to the user of the speech recognition system to determine if that is what the used intended when the user spoke.

Methods and apparatus for use in speech recognition systems for identifying unknown words and for adding previously unknown words to vocabularies and grammars of speech recognition systems

A natural language business system and method is developed to understand the underlying meaning of a person's speech, such as during a transaction with the business system. The system includes a speech recognition engine, and action classification engine, and a control module. The control module causes the system to execute an inventive method wherein the speech recognition and action classification models may be recursively optimized on an unisolated performance metric that is pertinent to the overall performance of the natural language business system, as opposed to the isolated model-specific criteria previously employed.

Natural language system and method based on unisolated performance metric

Methods and apparatus, in the context of speech recognition, for compensating in the cepstral domain for the effect of an interfering signal by using a reference signal.

Multi-channel codebook dependent compensation

Techniques for improving an automatic baseform generation system. More particularly, the invention provides techniques for reducing insertion of spurious speech events in a word or phone sequence generated by an automatic baseform generation system. Such automatic baseform generation techniques may be accomplished by enhancing the scores of long-lasting speech events with respect to the scores of short-lasting events. For example, this may be achieved by merging competing candidates that relate to the same speech event (e.g., phone or word) and that overlap in time into a single candidate, the score of which may be equal to the sum of the scores of the merged candidates.

Apparatus for reducing spurious insertions in speech recognition

An arrangement for yielding enhanced audio features towards the provision of enhanced audio-visual features for speech recognition. Input is provided in the form of noisy audio-visual features and noisy audio features related to the noisy audio-visual features.

Audio-visual codebook dependent cepstral normalization

Methods and arrangements for enhancing speech recognition in noisy environments, via providing at least one initial Compound Gaussian Mixture model, applying an adaptation algorithm to at least one item associated with speech enrollment data and to the at least one initial Compound Gaussian Mixture model to yield an intermediate output, and mathematically combining the at least one initial Compound Gaussian Mixture model with the intermediate output to yield an adapted Compound Gaussian Mixture model.

Adaptation of Compound Gaussian Mixture models

Methods for reducing spurious insertions in speech recognition

A technique for separating a signal associated with a first source from a mixture of the first source signal and a signal associated with a second source comprises the following steps/operations. First, two signals respectively representative of two mixtures of the first source signal and the second source signal are obtained. Then, the first source signal is separated from the mixture in a non-linear signal domain using the two mixture signals and at least one known statistical property associated with the first source and the second source, and without a need to use a reference signal.

Methods and apparatus for multiple source signal separation

Methods and apparatus for automatically deriving multiple phonetic baseforms of a word from a speech utterance of this word are provided in accordance with the present invention. In one embodiment, a method of automatically generating two or more phonetic baseforms from a spoken utterance representing a word includes the steps of: transforming the spoken utterance into a stream of acoustic observations; generating two or more strings of subphone units, wherein each string of subphone units represents a string of subphone units substantially maximizing a log-likelihood of the stream of acoustic observations, and wherein the log-likelihood is computed as a weighted sum of a transition score associated with a transition model and of an acoustic score associated with an acoustic model; and converting the two or more strings of subphone units into two or more phonetic baseforms.

Methods and apparatus for automatic generation of multiple pronunciations from acoustic data

Methods and apparatus for enhancing the accuracy and efficacy of speech recognition in an environment, such as the interior of an automobile or home, in which there may be significant ambient noise, such as music from loudspeakers within an automobile or programming from a television within a home.

Methods and apparatus for ambient noise removal in speech recognition

In connection with blind source separation, proposed herein, inter alia, are: expectation-maximization equations to iteratively estimate unmixing filters and source density parameters in the context of convolutive independent component analysis where the sources are modeled with mixtures of Gaussians; a scheme to estimate the length of unmixing filters; and two alternative initialization schemes.

Growing community of inventors

White Plains, NY, United States of America

Sabine V Deligne