At&t Intellectual Property I, LP

At+t Corp.

Lucent Technologies Inc.

Nuance Communications, Inc.

Bampton Technologies LLC

Mazin G Rahim

Srinivas Bangalore

Narendra Kumar Gupta

Giuseppe Riccardi

Gokhan Tur

Junlan Feng

Dilek Zeynep Hakkani-Tur

Allen Louis Gorin

Richard Vandervoort Cox

Bernard S Renger

David Crawford Gibbon

Behzad Shahraray

Lee Begeja

Zhu Liu

Patrick Guy Haffner

Steven Hart Lewis

Barbara B Hollister

Harris Drucker

Giuseppe Di Fabbrizio

Jeremy Huntley Wright

Juergen Schroeter

Bruce Melvin Buntschuh

Hossein Eslambolchi

Nambirajan Seshadri

Behzad Nadji

Stephen Michael Marcus

Robert Douglas Sharp

Robert Elias Schapire

Tirso M Alonso

Antony Van Der Mude

Benjamin J Stern

Ann K Syrdal

Biing-Hwang Juang

David Eugene Schulz

Shona Douglas

Wu Chou

Hiyan Alshawi

James M Wilson

Daniel Leon Stern

Yoram Singer

Dawn L Dutton

Ilana Bromberg

Lawrence Lyon Rose

Jay Gordon Wilpon

Chin-Hui Lee

Lawrence Kevin Saul

Piyush C Modi

Giuseppe DiFabrizzio

Giuseppe DiFabbrizio

Yariv Ephraim

Eric Rolfe Buhrke

Utterance data that includes at least a small amount of manually transcribed data is provided. Automatic speech recognition is performed on ones of the utterance data not having a corresponding manual transcription to produce automatically transcribed utterances. A model is trained using all of the manually transcribed data and the automatically transcribed utterances. A predetermined number of utterances not having a corresponding manual transcription are intelligently selected and manually transcribed. Ones of the automatically transcribed data as well as ones having a corresponding manual transcription are labeled. In another aspect of the invention, audio data is mined from at least one source, and a language model is trained for call classification from the mined audio data to produce a language model.

Unsupervised and active learning in automatic speech recognition for call classification

A system and method are disclosed that improve automatic speech recognition in a spoken dialog system. The method comprises partitioning speech recognizer output into self-contained clauses, identifying a dialog act in each of the self-contained clauses, qualifying dialog acts by identifying a current domain object and/or a current domain action, and determining whether further qualification is possible for the current domain object and/or current domain action. If further qualification is possible, then the method comprises identifying another domain action and/or another domain object associated with the current domain object and/or current domain action, reassigning the another domain action and/or another domain object as the current domain action and/or current domain object and then recursively qualifying the new current domain action and/or current object. This process continues until nothing is left to qualify.

System and method of spoken language understanding in human computer dialogs

A clausifier for extracting clauses for spoken language understanding is disclosed. The method relates to generating a set of clauses from speech utterance text and comprises inserting at least one boundary tag in speech utterance text related to sentence boundaries, inserting at least one edit tag indicating a portion of the speech utterance text to remove, and inserting at least one conjunction tag within the speech utterance text. The result is a set of clauses that may be identified within the speech utterance text according to the inserted at least one boundary tag, at least one edit tag and at least one conjunction tag. The disclosed clausifier comprises a sentence boundary classifier, an edit detector classifier, and a conjunction detector classifier. The clausifier may comprise a single classifier or a plurality of classifiers to perform the steps of identifying sentence boundaries, editing text, and identifying conjunctions within the text.

System and method of extracting clauses for spoken language understanding

A transceiver of a computing device may receive data from a query to provide to a search engine to perform a search. The computing device may negotiate, automatically to overcome a restriction to access a page of a set of top webpages in association with the search, a fee. A processor of the computing device may continue to search information associated with the query on the page using a machine learning function.

Searching restricted content on a network

A system and method are disclosed for generating customized text-to-speech voices for a particular application. The method comprises generating a custom text-to-speech voice by selecting a voice for generating a custom text-to-speech voice associated with a domain, collecting text data associated with the domain from a pre-existing text data source and using the collected text data, generating an in-domain inventory of synthesis speech units by selecting speech units appropriate to the domain via a search of a pre-existing inventory of synthesis speech units, or by recording the minimal inventory for a selected level of synthesis quality. The text-to-speech custom voice for the domain is generated utilizing the in-domain inventory of synthesis speech units. Active learning techniques may also be employed to identify problem phrases wherein only a few minutes of recorded data is necessary to deliver a high quality TTS custom voice.

System and method for generating customized text-to-speech voices

A clausifier and method of extracting clauses for spoken language understanding are disclosed. The method relates to generating a set of clauses from speech utterance text and comprises inserting at least one boundary tag in speech utterance text related to sentence boundaries, inserting at least one edit tag indicating a portion of the speech utterance text to remove, and inserting at least one conjunction tag within the speech utterance text. The result is a set of clauses that may be identified within the speech utterance text according to the inserted at least one boundary tag, at least one edit tag and at least one conjunction tag. The disclosed clausifier comprises a sentence boundary classifier, an edit detector classifier, and a conjunction detector classifier. The clausifier may comprise a single classifier or a plurality of classifiers to perform the steps of identifying sentence boundaries, editing text, and identifying conjunctions within the text.

A system and a method are provided. A speech recognition processor receives unconstrained input speech and outputs a string of words. The speech recognition processor is based on a numeric language that represents a subset of a vocabulary. The subset includes a set of words identified as being for interpreting and understanding number strings. A numeric understanding processor contains classes of rules for converting the string of words into a sequence of digits. The speech recognition processor utilizes an acoustic model database. A validation database stores a set of valid sequences of digits. A string validation processor outputs validity information based on a comparison of a sequence of digits output by the numeric understanding processor with valid sequences of digits in the validation database.

Recognizing the numeric language in natural spoken dialogue

Disclosed is a method for training a spoken dialog service component from website data. Spoken dialog service components typically include an automatic speech recognition module, a language understanding module, a dialog management module, a language generation module and a text-to-speech module. The method includes selecting anchor texts within a website based on a term density, weighting those anchor texts based on a percent of salient words to total words, and incorporating the weighted anchor texts into a live spoken dialog interface, the weights determining a level of incorporation into the live spoken dialog interface.

System and method of providing a spoken dialog interface to a website

The invention relates to a system and method for gathering data for use in a spoken dialog system. An aspect of the invention is generally referred to as an automated hidden human that performs data collection automatically at the beginning of a conversation with a user in a spoken dialog system. The method comprises presenting an initial prompt to a user, recognizing a received user utterance using an automatic speech recognition engine and classifying the recognized user utterance using a spoken language understanding module. If the recognized user utterance is not understood or classifiable to a predetermined acceptance threshold, then the method re-prompts the user. If the recognized user utterance is not classifiable to a predetermined rejection threshold, then the method transfers the user to a human as this may imply a task-specific utterance. The received and classified user utterance is then used for training the spoken dialog system.

System and method of providing an automated data-collection in spoken dialog systems

A system and method provides a natural language interface to world-wide web content. Either in advance or dynamically, webpage content is parsed using a parsing algorithm. A person using a telephone interface can provide speech information, which is converted to text and used to automatically fill in input fields on a webpage form. The form is then submitted to a database search and a response is generated. Information contained on the responsive webpage is extracted and converted to speech via a text-to-speech engine and communicated to the person.

Method and apparatus for automatically building conversational systems

Growing community of inventors

Warren, NJ, United States of America

Mazin G Rahim