Abstract: A method and system of training a spoken language understanding (SLU) model includes receiving natural language training data comprising (i) one or more speech recording, and (ii) a set of semantic entities and/or intents for each corresponding speech recording. For each speech recording, one or more entity labels and corresponding values, and one or more intent labels are extracted from the corresponding semantic entities and/or overall intent. A spoken language understanding (SLU) model is trained based upon the one or more entity labels and corresponding values, and one or more intent labels of the corresponding speech recordings without a need for a transcript of the corresponding speech recording.

Abstract: An illustrative embodiment includes a method for training an end-to-end (E2E) spoken language understanding (SLU) system. The method includes receiving a training corpus comprising a set of text classified using one or more sets of semantic labels but unpaired with speech and using the set of unpaired text to train the E2E SLU system to classify speech using at least one of the one or more sets of semantic labels. The method may include training a text-to-intent model using the set of unpaired text; and training a speech-to-intent model using the text-to-intent model. Alternatively or additionally, the method may include using a text-to-speech (TTS) system to generate synthetic speech from the unpaired text; and training the E2E SLU system using the synthetic speech.

Abstract: A method and system of training a spoken language understanding (SLU) model includes receiving natural language training data comprising (i) one or more speech recording, and (ii) a set of semantic entities and/or intents for each corresponding speech recording. For each speech recording, one or more entity labels and corresponding values, and one or more intent labels are extracted from the corresponding semantic entities and/or overall intent. A spoken language understanding (SLU) model is trained based upon the one or more entity labels and corresponding values, and one or more intent labels of the corresponding speech recordings without a need for a transcript of the corresponding speech recording.

Abstract: An illustrative embodiment includes a method for training an end-to-end (E2E) spoken language understanding (SLU) system. The method includes receiving a training corpus comprising a set of text classified using one or more sets of semantic labels but unpaired with speech and using the set of unpaired text to train the E2E SLU system to classify speech using at least one of the one or more sets of semantic labels. The method may include training a text-to-intent model using the set of unpaired text; and training a speech-to-intent model using the text-to-intent model. Alternatively or additionally, the method may include using a text-to-speech (TTS) system to generate synthetic speech from the unpaired text; and training the E2E SLU system using the synthetic speech.

Abstract: Systems and methods for processing a query include determining a plurality of sets of match candidates for a query using a processor, each of the plurality of sets of match candidates being independently determined from a plurality of diverse word lattice generation components of different type. The plurality of sets of match candidates is merged by generating a first score for each match candidate to provide a merged set of match candidates. A second score is computed for each match candidate of the merged set based upon features of that match candidate. The first score and the second score are combined to provide a final set of match candidates as matches to the query.

Abstract: Systems and methods for processing a query include determining a plurality of sets of match candidates for a query using a processor, each of the plurality of sets of match candidates being independently determined from a plurality of diverse word lattice generation components of different type. The plurality of sets of match candidates is merged by generating a first score for each match candidate to provide a merged set of match candidates. A second score is computed for each match candidate of the merged set based upon features of that match candidate. The first score and the second score are combined to provide a final set of match candidates as matches to the query.

Abstract: Techniques for assisting in translation are provided. A speech recognition hypothesis is obtained, corresponding to a source language utterance. Information retrieval is performed on a supplemental database, based on a situational context, to obtain at least one word string that is related to the source language utterance. The speech recognition hypothesis and the word string are then formatted for display to a user, to facilitate an appropriate selection by the user for translation.

Abstract: A call routing system is created by receiving a set of initial target classes and a corresponding set of topic descriptions. Non-overlapping semantic tokens in the set of topic descriptions are identified. A set of clear target classes from the non-overlapping semantic tokens and the initial target classes is identified. Overlapping semantic tokens from the set of topic descriptions are identified. A set of vague classes is identified from the overlapping semantic tokens and the initial target classes. A set of disambiguation dialogues and a set of grammar prompts is generated according to the overlapping and non-overlapping semantic tokens. The call routing system is then created based on the set of clear target classes, the set of vague target classes, and the set of disambiguation dialogues.

Abstract: A system and method for representing call content in a searchable database includes transcribing call content to text. The call content is projected to vector space, by creating a vector by indexing the call based on the content and determining a similarity of the call to an atomic-class dictionary. The call is classified in a relational database in accordance with the vector.

Abstract: A call routing system is created by receiving a set of initial target classes and a corresponding set of topic descriptions. Non-overlapping semantic tokens in the set of topic descriptions are identified. A set of clear target classes from the non-overlapping semantic tokens and the initial target classes is identified. Overlapping semantic tokens from the set of topic descriptions are identified. A set of vague classes is identified from the overlapping semantic tokens and the initial target classes. A set of disambiguation dialogues and a set of grammar prompts is generated according to the overlapping and non-overlapping semantic tokens. The call routing system is then created based on the set of clear target classes, the set of vague target classes, and the set of disambiguation dialogues.

Abstract: A technique for context adaptation of a speech-to-speech translation system is provided. A plurality of sets of paralinguistic attribute values is obtained from a plurality of input signals. Each set of the plurality of sets of paralinguistic attribute values is extracted from a corresponding input signal of the plurality of input signals via a corresponding classifier of a plurality of classifiers. A final set of paralinguistic attribute values is generated for the plurality of input signals from the plurality of sets of paralinguistic attribute values. Performance of at least one of a speech recognition module, a translation module and a text-to-speech module of the speech-to-speech translation system is modified in accordance with the final set of paralinguistic attribute values for the plurality of input signals.

Abstract: Techniques for assisting in translation are provided. A speech recognition hypothesis is obtained, corresponding to a source language utterance. Information retrieval is performed on a supplemental database, based on a situational context, to obtain at least one word string that is related to the source language utterance. The speech recognition hypothesis and the word string are then formatted for display to a user, to facilitate an appropriate selection by the user for translation.

Abstract: Techniques for assisting in translation are provided A speech recognition hypothesis is obtained, corresponding to a source language utterance. Information retrieval is performed on a supplemental database, based on a situational context, to obtain at least one word string that is related to the source language utterance. The speech recognition hypothesis and the word string are then formatted for display to a user, to facilitate an appropriate selection by the user for translation.

Abstract: Techniques for assisting in translation are provided. A speech recognition hypothesis is obtained, corresponding to a source language utterance. Information retrieval is performed on a supplemental database, based on a situational context, to obtain at least one word string that is related to the source language utterance. The speech recognition hypothesis and the word string are then formatted for display to a user, to facilitate an appropriate selection by the user for translation.

Abstract: A system and method for representing call content in a searchable database includes transcribing call content to text. The call content is projected to vector space, by creating a vector by indexing the call based on the content and determining a similarity of the call to an atomic-class dictionary. The call is classified in a relational database in accordance with the vector.

Abstract: A system and method for representing call content in a searchable database includes transcribing call content to text. The call content is projected to vector space, by creating a vector by indexing the call based on the content and determining a similarity of the call to an atomic-class dictionary. The call is classified in a relational database in accordance with the vector.

Abstract: Techniques for assisting in translation are provided. A speech recognition hypothesis is obtained, corresponding to a source language utterance. Information retrieval is performed on a supplemental database, based on a situational context, to obtain at least one word string that is related to the source language utterance. The speech recognition hypothesis and the word string are then formatted for display to a user, to facilitate an appropriate selection by the user for translation.

Abstract: A technique for context adaptation of a speech-to-speech translation system is provided. A plurality of sets of paralinguistic attribute values is obtained from a plurality of input signals. Each set of the plurality of sets of paralinguistic attribute values is extracted from a corresponding input signal of the plurality of input signals via a corresponding classifier of a plurality of classifiers. A final set of paralinguistic attribute values is generated for the plurality of input signals from the plurality of sets of paralinguistic attribute values. Performance of at least one of a speech recognition module, a translation module and a text-to-speech module of the speech-to-speech translation system is modified in accordance with the final set of paralinguistic attribute values for the plurality of input signals.

Abstract: A method and apparatus for performing discriminative training of, for example, call routing training data (or, alternatively, other classification training data) which improves the subsequent classification of a user's natural language based requests. An initial scoring matrix is generated based on the training data and then the scoring matrix is adjusted so as to improve the discrimination between competing classes (e.g., destinations). In accordance with one illustrative embodiment of the present invention a Generalized Probabilistic Descent (GPD) algorithm may be advantageously employed to provide the improved discrimination.

Abstract: A method and apparatus for performing discriminative training of, for example, call routing training data (or, alternatively, other classification training data) which improves the subsequent classification of a user's natural language based requests. An initial scoring matrix is generated based on the training data and then the scoring matrix is adjusted so as to improve the discrimination between competing classes (e.g., destinations). In accordance with one illustrative embodiment of the present invention a Generalized Probabilistic Descent (GPD) algorithm may be advantageously employed to provide the improved discrimination.