Google Inc.

At&t Intellectual Property I, LP

Nuance Communications, Inc.

Cyril Georges Luc Allauzen

Johan Schalkwyk

Sarangarajan Parthasarathy

Michael Dennis Riley

Ciprian Ioan Chelba

Hasim Sak

Michael H Cohen

Brandon M Ballinger

Edward Oscar Benson

Yun-hsuan Sung

Javier Gonzalvo Fructuoso

Alexander Gutkin

A method, apparatus and machine-readable medium are provided. A phonotactic grammar is utilized to perform speech recognition on received speech and to generate a phoneme lattice. A document shortlist is generated based on using the phoneme lattice to query an index. A grammar is generated from the document shortlist. Data for each of at least one input field is identified based on the received speech and the generated grammar.

System and method for robust access and entry to large structured data using voice form-filling

Methods, computer program products and systems are described for converting speech to text. Sound information is received at a computer server system from an electronic device, where the sound information is from a user of the electronic device. A context identifier indicates a context within which the user provided the sound information. The context identifier is used to select, from among multiple language models, a language model appropriate for the context. Speech in the sound information is converted to text using the selected language model. The text is provided for use by the electronic device.

Language model selection for speech-to-text conversion

A system is configured to receive a first string corresponding to an interpretation of a natural-language user voice entry; provide a representation of the first string as feedback to the natural-language user voice entry; receive, based on the feedback, a second string corresponding to a natural-language corrective user entry, where the natural-language corrective user entry may correspond to a correction to the natural-language user voice entry; parse the second string into one or more tokens; determine at least one corrective instruction from the one or more tokens of the second string; generate, from at least a portion of each of the first and second strings and based on the at least one corrective instruction, candidate corrected user entries; select a corrected user entry from the candidate corrected user entries; and output the selected, corrected user entry.

Natural language correction for speech input

An automatic speech recognition system and method are provided for written-domain language modeling. According to one implementation, a process includes accessing decomposed training data that results from applying rewrite grammar rules to original training data, the decomposed training data comprising (i) regular words from the original training data that have not been rewritten using the set of rewrite grammar rules, and (ii) decomposed segments that result from rewriting non-lexical entities from the original training data using the rewrite grammar rules, generating a restriction model that (i) maps language model paths for regular words to themselves, and (ii) restricts language model paths for decomposed segments for non-lexical entities, training a n-gram language model over the training data, composing the restriction model and the language model to obtain a restricted language model, and constructing a decoding network by composing a context dependency model and a pronunciation lexicon with the restricted language model.

Written-domain language modeling with decomposition

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for providing statistical unit selection language modeling based on acoustic fingerprinting. The methods, systems and apparatus include the actions of obtaining a unit database of acoustic units and, for each acoustic unit, linguistic data corresponding to the acoustic unit; obtaining stored data associating each acoustic unit with (i) a corresponding acoustic fingerprint and (ii) a probability of the linguistic data corresponding to the acoustic unit occurring in a text corpus; determining that the unit database of acoustic units has been updated to include one or more new acoustic units; for each new acoustic unit in the updated unit database: generating an acoustic fingerprint for the new acoustic unit; identifying an acoustic unit that (i) has an acoustic fingerprint that is indicated as similar to the fingerprint of the new acoustic unit, and (ii) has a stored associated probability.

Statistical unit selection language models based on acoustic fingerprinting

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for creating a static language model from a mixture of n-gram language models. One of the methods includes receiving a set of development sentences W, receiving a set of language models G, determining a set of n-gram language model weights &#x3bb;based on the development sentences W and the set of language models G, determining a set of sentence cluster weights &#x3b3;, each of the sentence cluster weights corresponding to a cluster in a set of sentence clusters, each cluster in the set of sentence clusters associated with at least one sentence from the set of development sentences W, and generating a language model from the set of language models G, the set of n-gram language model weights &#x3bb;, the set of sentence clusters, and the set of sentence cluster weights &#x3b3;.

Mixture of n-gram language models

A data processing apparatus is configured to receive a first string related to a natural-language voice user entry and a second string including at least one natural-language refinement to the user entry; parse the first string into a first set of one or more tokens and the second string into a second set of one or more tokens; determine at least one refining instruction from the second set of one or more tokens; generate, from at least a portion of each of the first string and the second string and based on the at least one refining instruction, a group of candidate refined user entries; select a refined user entry from the group of candidate refined user entries; and output the selected, refined user entry.

Natural language refinement of voice and text entry

Methods, computer program products and systems are described for speech-to-text conversion. A voice input is received from a user of an electronic device and contextual metadata is received that describes a context of the electronic device at a time when the voice input is received. Multiple base language models are identified, where each base language model corresponds to a distinct textual corpus of content. Using the contextual metadata, an interpolated language model is generated based on contributions from the base language models. The contributions are weighted according to a weighting for each of the base language models. The interpolated language model is used to convert the received voice input to a textual output. The voice input is received at a computer server system that is remote to the electronic device. The textual output is transmitted to the electronic device.

Growing community of inventors

Long Island City, NY, United States of America

Cyril Georges Luc Allauzen