International Business Machines Corporation

Texas Instruments Corporation

Abraham P Ittycheriah

Stephane Herman Maes

Paul Andrew Moskowitz

Michael Alan Picheny

Jan Sedivy

James Campbell Colson

Jeffrey Scott Sorensen

Salim Estephan Roukos

Neal J Alewine

Nandakishore Kambhatla

Barbara J Wheatley

Xiaoqiang Luo

Hongyan Jing

Chandrasekhar Narayanaswami

Bhuvana Ramabhadran

David Nahamoo

Maria Elena Smith

Raimo Bakis

Radu Florian

Michael Daniel Monkowski

Edward Adam Epstein

Robert T Ward

Kishore A Papineni

Charles T Rutherfoord

Stephen Graham Lawrence

Peter Thomas Brunet

Steven J Friedland

Cezar Pendus

Yaser Al-Onaizan

Leiming R Qian

Hari Chittaluru

Jian-Ming Xu

Jeffrey L Scruggs

Jeffrey S Sorenson

Kenneth Davies

Vladimir Bergl

A method includes translating a source to generate a translated source, extracting a set of terms from one of the source and the translated source comprising at least a first term and a second term related to the first term, comparing the extracted set of terms with at least one translation pair, and determining a correct translation based on the comparison.

Translation using related term pairs

Techniques for translating and presenting text in a structured document are provided. A structured document including text to be translated is received. At least one portion of the text to be translated is translated into at least one representation of translated text of a specific language. The translation is carried out in accordance with a prioritization schedule. Further, the representation of translated text is provided by at least first and second servers, the first server independently providing the representation of translated text of a first quality and the second server independently providing the representation of translated text of a second quality, the first quality being different than the second quality. As the text is translated, the representation of translated text is presented immediately when available.

Prioritized incremental asynchronous machine translation of structured documents

A Bell Tree data structure is provided to model the process of chaining the mentions, from one or more documents, into entities, tracking the entire process; where the data structure is used in an entity tracking process that produces multiple results ranked by a product of probability scores.

Mention-synchronous entity tracking: system and method for chaining mentions

An audio splitting system for sharing speech data associated with the same utterance between multiple speech technologies (consumers). In one aspect, the system comprises one or more queues for storing data, a plurality of consumers each sharing the data stored in the one or more queues and a scheduler for managing the storage of the data in the one or more queues and the consumption of the data in the one or more queues by each of the plurality of consumers. The consumers will register their data requirements and priority requests with the scheduler. The scheduler assigns each of the plurality of consumers to one or more of the queues based on the registered data requirements.

Systems and methods for processing audio using multiple speech technologies

A method, computer program product and system are provided. The method includes the steps of: providing output text and a confidence value and displaying the output text. The output text includes text in a second language produced from machine translation performed on input text in a first language. The confidence value corresponds to an indication of reliability of the output text. The display of the output text includes a display attribute corresponding to the confidence value of the output text.

Visualization method for machine translation

Mention-synchronous entity tracking system and method for chaining mentions

A system and method for signal analysis in a network. The method includes attempting, by a first processor, to compute optimal coefficients for filtering a signal, determining that computing the optimal coefficients exceeds the computational capabilities of the first processor, notifying a second processor that computing the optimal coefficients exceeds the computational capabilities of the first processor, and computing, by the second processor, the optimal coefficients. The system and method account for limited computational resources allocated to certain processors in a telecommunications system.

System and method for analysis and filtering of signals in a telecommunications network

System and methods for processing audio using multiple speech technologies

In a text-to-speech system, a method of converting text-to-speech can include receiving a text input and comparing the received text input to at least one entry in a text-to-speech cache memory. Each entry in the text-to-speech cache memory can specify a corresponding spoken output. If the text input matches one of the entries in the text-to-speech cache memory, the cached speech output specified by the matching entry can be provided.

Method and system for text-to-speech caching

A system and method for building compressed biometric models and performing biometric identification using such models. The use of the compressed biometric models results in a significant decrease in the storage requirements for biometric models in conventional biometric systems. A given number of L reference biometric models are built. The L reference models are randomly divided into M subsets. During user enrollment, distance measurements between a temporary biometric model and each of the reference models in the M subsets are computed. The rank and distance parameters are used to build the compressed biometric models in accordance with the model: I(M , R , D(M , R )), where I represents the identity of the closest reference model in a corresponding subset M ; R refers to the ranking of the closeness of the reference model to the temporary biometric model as compared with the closeness of each of the other reference models in the corresponding subset M ; and D refers to the corresponding distance measure between the reference model and the temporary biometric model.

System and method for compressing biometric models

A system of mobile units are installed in multiple vehicles in traffic, the vehicles with mobile units being a sample of all vehicles in traffic. These mobile units include both wireless communications devices and apparatus that determines the location of each vehicle. Monitoring a vehicle's position as a function of time also reveals the velocity of the vehicle. Position and speed information is periodically broadcast by the vehicles to a central monitoring station and to neighboring vehicles. At the central monitoring station, the collective input from the sample set of vehicles is processed using statistical analysis methods to provide an instant chart of traffic conditions in the area, the accuracy of said chart being within a range determined by the size of the sample. Warnings of delays or updates on traffic conditions on the road ahead are then automatically returned to subscribers of the information or are used as part of an Intelligent Vehicle Highway System (IVHS). Neighboring vehicles within a region communicating with one another form a network in which the broadcast information is processed locally on the respective vehicles to estimate possible problems ahead and consider computing an alternate road and/or checking with the central monitoring station for more information. If out of range of the central monitoring station, the vehicles in the network form a local area network for the exchange and update of information, and when any vehicle in the network is within range of the central monitoring station, the local area network data is uploaded to help update the overall traffic information.

Automated traffic mapping using sampling and analysis

A method of identifying homophones of a word uttered by a user from at least a portion of existing words of a vocabulary of a speech recognition engine comprises the steps of: a user uttering the word; decoding the uttered word; computing respective measures between the decoded word and at least a portion of the other existing vocabulary words, the respective measures indicative of acoustic similarity between the word and the at least a portion of other existing words; if at least one measure is within a threshold range, indicating, to the user, results associated with the at least one measure, the results preferably including the decoded word and the other existing vocabulary word associated with the at least one measure; and the user preferably making a selection depending on the word the user intended to utter.

Apparatus and methods for identifying homophones among words in a speech recognition system

Apparatus for preventing unauthorized use of a voice dialing system and, particularly, a call forwarding feature associated with the system whereby system users may forward a telephone number respectively associated therewith to a remote location in order to receive phone calls at the remote location, comprises: a database for pre-storing telephone numbers of system users and for pre-storing acoustic models respectively representative of speech associated with each system user, the acoustic models respectively corresponding to the telephone numbers; and a speaker identification module operatively coupled to the database for obtaining and decoding a speech sample from a potential system user during the potential users' attempt to make a telephone call, the speaker identification module comparing the decoded speech sample obtained with the pre-stored acoustic model associated with the telephone number dialed by the potential user; whereby if the decoded speech sample substantially matches the pre-stored acoustic model, then the phone call attempted by the potential user is terminated.

Apparatus and methods for user identification to deny access or service to unauthorized users

A method of training at least one new word for addition to a vocabulary of a speech recognition engine containing existing words comprises the steps of: a user uttering the at least one new word; computing respective measures between the at least one newly uttered word and at least a portion of the existing vocabulary words, the respective measures indicative of acoustic similarity between the at least one word and the at least a portion of existing words; if no measure is within the threshold range, automatically adding the at least one newly uttered word to the vocabulary; and if at least one measure is within a threshold range, refraining from automatically adding the at least one newly uttered word to the vocabulary.

Apparatus and methods for rejecting confusible words during training associated with a speech recognition system

A method of determining potential acoustic confusion between at least one new word and at least a portion of existing words of a vocabulary of a speech recognition engine comprises the steps of: a user inputting the at least one new word; computing respective measures between the at least one new word and the at least a portion of existing vocabulary words, the respective measures indicative of acoustic similarity between the at least one word and the at least a portion of existing words; if at least one measure is within a threshold range, indicating results associated with the at least one measure and prompting the user to input an alternative word or additional information pertaining to the at least one new word; and if no measure is within the threshold range, adding the at least one new word to the vocabulary.

Apparatus and methods for identifying potential acoustic confusibility among words in a speech recognition system

Growing community of inventors

Danbury, CT, United States of America

Abraham P Ittycheriah