Patents by Inventor Giuseppe Riccardi
Giuseppe Riccardi has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 7966174Abstract: A system for recognizing patterns is disclosed. Grammar learning from a corpus includes, for the other non-context words, generating frequency vectors for each non-context token in a corpus based upon counted occurrences of a predetermined relationship of the non-context tokens to identified context tokens. Clusters are grown from the frequency vectors according to a lexical correlation or a cluster tree among the non-context tokens. The cluster tree is used for pattern recognition.Type: GrantFiled: February 14, 2008Date of Patent: June 21, 2011Assignee: AT&T Intellectual Property II, L.P.Inventors: Srinivas Bangalore, Giuseppe Riccardi
-
Patent number: 7957971Abstract: Word lattices that are generated by an automatic speech recognition system are used to generate a modified word lattice that is usable by a spoken language understanding module. In one embodiment, the spoken language understanding module determines a set of salient phrases by calculating an intersection of the modified word lattice, which is optionally preprocessed, and a finite state machine that includes a plurality of salient grammar fragments.Type: GrantFiled: June 12, 2009Date of Patent: June 7, 2011Assignee: AT&T Intellectual Property II, L.P.Inventors: Allen Louis Gorin, Dilek Z. Hakkani-Tur, Giuseppe Riccardi, Gokhan Tur, Jeremy Huntley Wright
-
Patent number: 7869998Abstract: A voice-enabled help desk service is disclosed. The service comprises an automatic speech recognition module for recognizing speech from a user, a spoken language understanding module for understanding the output from the automatic speech recognition module, a dialog management module for generating a response to speech from the user, a natural voices text-to-speech synthesis module for synthesizing speech to generate the response to the user, and a frequently asked questions module. The frequently asked questions module handles frequently asked questions from the user by changing voices and providing predetermined prompts to answer the frequently asked question.Type: GrantFiled: December 19, 2002Date of Patent: January 11, 2011Assignee: AT&T Intellectual Property II, L.P.Inventors: Giuseppe Di Fabbrizio, Dawn L Dutton, Narendra K. Gupta, Barbara B. Hollister, Mazin G Rahim, Giuseppe Riccardi, Robert Elias Schapire, Juergen Schroeter
-
Patent number: 7860713Abstract: Systems and methods for annotating speech data. The present invention reduces the time required to annotate speech data by selecting utterances for annotation that will be of greatest benefit. A selection module uses speech models, including speech recognition models and spoken language understanding models, to identify utterances that should be annotated based on criteria such as confidence scores generated by the models. These utterances are placed in an annotation list along with a type of annotation to be performed for the utterances and an order in which the annotation should proceed. The utterances in the annotation list can be annotated for speech recognition purposes, spoken language understanding purposes, labeling purposes, etc. The selection module can also select utterances for annotation based on previously annotated speech data and deficiencies in the various models.Type: GrantFiled: July 1, 2008Date of Patent: December 28, 2010Assignee: AT&T Intellectual Property II, L.P.Inventors: Tirso M. Alonso, Ilana Bromberg, Dilek Z. Hakkani-Tur, Barbara B. Hollister, Mazin G. Rahim, Giuseppe Riccardi, Lawrence Lyon Rose, Daniel Leon Stern, Gokhan Tur, James M. Wilson
-
Patent number: 7729902Abstract: A method is disclosed for designing a labeling guide for use by a labeler in labeling data used for training a spoken language understanding (SLU) module for an application. The method comprises a labeling guide designer selecting domain-independent actions applicable to an application, selecting domain-dependent objects according to characteristics of the application, and generating a labeling guide using the selected domain-independent actions and selected domain-dependent objects. An advantage of the labeling guide generated in this manner is that the labeling guide designer can easily port the labeling guide to a new application by selecting a set of domain-independent action and then selecting the domain-dependent objects related to the new application.Type: GrantFiled: October 30, 2007Date of Patent: June 1, 2010Assignee: AT&T Intellectual Property II, L.P.Inventors: Narendra K. Gupta, Barbara B. Hollister, Mazin G. Rahim, Giuseppe Riccardi
-
Publication number: 20100049519Abstract: 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.Type: ApplicationFiled: November 5, 2009Publication date: February 25, 2010Applicant: AT&T Corp.Inventors: Mazin G. Rahim, Giuseppe Riccardi, Jeremy Huntley Wright, Bruce Melvin Buntschuh, Allen Louis Gorin
-
Patent number: 7624015Abstract: 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.Type: GrantFiled: March 2, 2006Date of Patent: November 24, 2009Assignee: AT&T Intellectual Property II, L.P.Inventors: Mazin G. Rahim, Giuseppe Riccardi, Jeremy Huntley Wright, Bruce Melvin Buntschuh, Allen Louis Gorin
-
Patent number: 7620548Abstract: The invention concerns a method and system for detecting morphemes in a user's communication. The method may include recognizing a lattice of phone strings from the user's input communication, the lattice representing a distribution over the phone strings, and detecting morphemes in the user's input communication using the lattice. The morphemes may be acoustic and/or non-acoustic. The morphemes may represent any unit or sub-unit of communication including phones, diphones, phone-phrases, syllables, grammars, words, gestures, tablet strokes, body movements, mouse clicks, etc. The training speech may be verbal, non-verbal, a combination of verbal and non-verbal, or multimodal.Type: GrantFiled: September 13, 2007Date of Patent: November 17, 2009Assignee: AT&T Intellectual Property II, L.P.Inventors: Allen Louis Gorin, Dijana Petrovska-Delacretaz, Giuseppe Riccardi, Jeremy Huntley Wright
-
Patent number: 7603272Abstract: Disclosed is a system and method of decomposing a lattice transition matrix into a block diagonal matrix. The method is applicable to automatic speech recognition but can be used in other contexts as well, such as parsing, named entity extraction and any other methods. The method normalizes the topology of any input graph according to a canonical form.Type: GrantFiled: June 19, 2007Date of Patent: October 13, 2009Assignee: AT&T Intellectual Property II, L.P.Inventors: Dilek Z. Hakkani-Tur, Giuseppe Riccardi
-
Publication number: 20090248416Abstract: Word lattices that are generated by an automatic speech recognition system are used to generate a modified word lattice that is usable by a spoken language understanding module. In one embodiment, the spoken language understanding module determines a set of salient phrases by calculating an intersection of the modified word lattice, which is optionally preprocessed, and a finite state machine that includes a plurality of salient grammar fragments.Type: ApplicationFiled: June 12, 2009Publication date: October 1, 2009Applicant: AT&T Corp.Inventors: Allen Louis Gorin, Dilek Z. Hakkani-Tur, Giuseppe Riccardi, Gokhan Tur, Jeremy Huntley Wright
-
Publication number: 20090198493Abstract: A system and method is provided for combining active and unsupervised learning for automatic speech recognition. This process enables a reduction in the amount of human supervision required for training acoustic and language models and an increase in the performance given the transcribed and un-transcribed data.Type: ApplicationFiled: March 30, 2009Publication date: August 6, 2009Applicant: AT&T Corp.Inventors: Dilek Zeynep Hakkani-Tur, Giuseppe Riccardi
-
Patent number: 7571098Abstract: Word lattices that are generated by an automatic speech recognition system are used to generate a modified word lattice that is usable by a spoken language understanding module. In one embodiment, the spoken language understanding module determines a set of salient phrases by calculating an intersection of the modified word lattice, which is optionally preprocessed, and a finite state machine that includes a plurality of salient grammar fragments.Type: GrantFiled: May 29, 2003Date of Patent: August 4, 2009Assignee: AT&T Intellectual Property II, L.P.Inventors: Allen Louis Gorin, Dilek Z. Hakkani-Tur, Giuseppe Riccardi, Gokhan Tur, Jeremy Huntley Wright
-
Patent number: 7562014Abstract: A large amount of human labor is required to transcribe and annotate a training corpus that is needed to create and update models for automatic speech recognition (ASR) and spoken language understanding (SLU). Active learning enables a reduction in the amount of transcribed and annotated data required to train ASR and SLU models. In one aspect of the present invention, an active learning ASR process and active learning SLU process are coupled, thereby enabling further efficiencies to be gained relative to a process that maintains an isolation of data in both the ASR and SLU domains.Type: GrantFiled: September 26, 2007Date of Patent: July 14, 2009Assignee: AT&T Intellectual Property II, L.P.Inventors: Dilek Z Hakkani-Tur, Mazin G Rahim, Giuseppe Riccardi, Gokhan Tur
-
Patent number: 7562010Abstract: Systems and methods for determining word confidence scores. Speech recognition systems generate a word lattice for speech input. Posterior probabilities of the words in the word lattice are determined using a forward-backward algorithm. Next, time slots are defined for the word lattice, and for all transitions that at least partially overlap a particular time slot, the posterior probabilities of transitions that have the same word label are combined for those transitions. The combined posterior probabilities are used as confidence scores. A local entropy can be computed on the competitor transitions of a particular time slot and also used as a confidence score.Type: GrantFiled: June 23, 2006Date of Patent: July 14, 2009Assignee: AT&T Intellectual Property II, L.P.Inventors: Roberto Gretter, Giuseppe Riccardi
-
Patent number: 7533019Abstract: A system and method is provided for combining active and unsupervised learning for automatic speech recognition. This process enables a reduction in the amount of human supervision required for training acoustic and language models and an increase in the performance given the transcribed and un-transcribed data.Type: GrantFiled: December 23, 2003Date of Patent: May 12, 2009Assignee: AT&T Intellectual Property II, L.P.Inventors: Dilek Zeynep Hakkani-Tür, Giuseppe Riccardi
-
Publication number: 20090070113Abstract: A voice-enabled help desk service is disclosed. The service comprises an automatic speech recognition module for recognizing speech from a user, a spoken language understanding module for understanding the output from the automatic speech recognition module, a dialog management module for generating a response to speech from the user, a natural voices text-to-speech synthesis module for synthesizing speech to generate the response to the user, and a frequently asked questions module. The frequently asked questions module handles frequently asked questions from the user by changing voices and providing predetermined prompts to answer the frequently asked question.Type: ApplicationFiled: November 7, 2008Publication date: March 12, 2009Applicant: AT&T Corp.Inventors: Narendra K. Gupta, Mazin G. Rahim, Giuseppe Riccardi
-
Publication number: 20080288244Abstract: In an embodiment, a lattice of phone strings in an input communication of a user may be recognized, wherein the lattice may represent a distribution over the phone strings. Morphemes in the input communication of the user may be detected using the recognized lattice. Task-type classification decisions may be made based on the detected morphemes in the input communication of the user.Type: ApplicationFiled: July 30, 2008Publication date: November 20, 2008Applicant: AT&T Corp.Inventors: Allen Louis Gorin, Dijana Petrovska-Delacretaz, Giuseppe Riccardi, Jeremy Huntley Wright
-
Patent number: 7451089Abstract: A voice-enabled help desk service is disclosed. The service comprises an automatic speech recognition module for recognizing speech from a user, a spoken language understanding module for understanding the output from the automatic speech recognition module, a dialog management module for generating a response to speech from the user, a natural voices text-to-speech synthesis module for synthesizing speech to generate the response to the user, and a frequently asked questions module. The frequently asked questions module handles frequently asked questions from the user by changing voices and providing predetermined prompts to answer the frequently asked question.Type: GrantFiled: February 15, 2007Date of Patent: November 11, 2008Assignee: AT&T Intellectual Property II, L.P.Inventors: Narendra K. Gupta, Mazin G. Rahim, Giuseppe Riccardi
-
Publication number: 20080270130Abstract: Systems and methods for annotating speech data. The present invention reduces the time required to annotate speech data by selecting utterances for annotation that will be of greatest benefit. A selection module uses speech models, including speech recognition models and spoken language understanding models, to identify utterances that should be annotated based on criteria such as confidence scores generated by the models. These utterances are placed in an annotation list along with a type of annotation to be performed for the utterances and an order in which the annotation should proceed. The utterances in the annotation list can be annotated for speech recognition purposes, spoken language understanding purposes, labeling purposes, etc. The selection module can also select utterances for annotation based on previously annotated speech data and deficiencies in the various models.Type: ApplicationFiled: July 1, 2008Publication date: October 30, 2008Applicant: AT&T Corp.Inventors: Tirso M. Alonso, Ilana Bromberg, Dilek Z. Hakkani-Tur, Barbara B. Hollister, Mazin G. Rahim, Giuseppe Riccardi, Lawrence Lyon Rose, Daniel Leon Stern, Gokhan Tur, James M. Wilson
-
Patent number: 7440897Abstract: In an embodiment, a lattice of phone strings in an input communication of a user may be recognized, wherein the lattice may represent a distribution over the phone strings. Morphemes in the input communication of the user may be detected using the recognized lattice. Task-type classification decisions may be made based on the detected morphemes in the input communication of the user.Type: GrantFiled: May 27, 2006Date of Patent: October 21, 2008Assignee: AT&T Corp.Inventors: Allen Louis Gorin, Dijana Petrovska-Delacretaz, Giuseppe Riccardi, Jeremy Huntley Wright