Google Inc.

Olivier Siohan

Francoise Beaufays

Brian Strope

Pedro Jose Moreno Mengibar

Ignacio Lopez Moreno

Eugene Weinstein

Olga Kapralova

Takaki Makino

John Paul Alex

Joseph A Nelson

Richard Cameron Rose

Pedro J Mengibar

Basilio Garcia Castillo

Otavio Braga

Hank Liao

Ryan Mcdonald

Basilio Garcia

Kishan Sachdeva

Benyah Shaparenko

Joshua Maynez

A method () includes receiving audio data () corresponding to an utterance () spoken by a user (), receiving video data () representing motion of lips of the user while the user was speaking the utterance, and obtaining multiple candidate transcriptions () for the utterance based on the audio data. For each candidate transcription of the multiple candidate transcriptions, the method also includes generating a synthesized speech representation () of the corresponding candidate transcription and determining an agreement score () indicating a likelihood that the synthesized speech representation matches the motion of the lips of the user while the user speaks the utterance. The method also includes selecting one of the multiple candidate transcriptions for the utterance as a speech recognition output () based on the agreement scores determined for the multiple candidate transcriptions for the utterance.

Rescoring automatic speech recognition hypotheses using audio-visual matching

Implementations relate to an application that can bias automatic speech recognition for meetings using data that may be associated with the meeting and/or meeting participants. A transcription of inputs provided during a meeting can additionally and/or alternatively be processed to determine whether the inputs should be incorporated into a meeting document, which can provide a summary for the meeting. In some instances, entries into a meeting document can be designated as action items, and those action items can optionally have conditions for reminding meeting participants about the action items and/or for determining whether an action item has been fulfilled. In this way, various tasks that may typically be manually performed by meeting participants, such as creating a meeting summary, can be automated in a more accurate manner. This can preserve resources that may otherwise be wasted during video conferences, in-person meetings, and/or other gatherings.

Meeting speech biasing and/or document generation based on meeting content and/or related data

The subject matter of this specification can be embodied in, among other things, a method that includes receiving an audio signal and initiating speech recognition tasks by a plurality of speech recognition systems (SRS's). Each SRS is configured to generate a recognition result specifying possible speech included in the audio signal and a confidence value indicating a confidence in a correctness of the speech result. The method also includes completing a portion of the speech recognition tasks including generating one or more recognition results and one or more confidence values for the one or more recognition results, determining whether the one or more confidence values meets a confidence threshold, aborting a remaining portion of the speech recognition tasks for SRS's that have not generated a recognition result, and outputting a final recognition result based on at least one of the generated one or more speech results.

Speech recognition with parallel recognition tasks

Methods, systems, and apparatus are described that receive audio data for an utterance. Association data is accessed that indicates associations between data corresponding to uncorrupted audio segments, and data corresponding to corrupted versions of the uncorrupted audio segments, where the associations are determined before receiving the audio data for the utterance. Using the association data and the received audio data for the utterance, data corresponding to at least one uncorrupted audio segment is selected. A transcription of the utterance is determined based on the selected data corresponding to the at least one uncorrupted audio segment.

Speech recognition using associative mapping

The present disclosure relates to training a speech recognition system. One example method includes receiving a collection of speech data items, wherein each speech data item corresponds to an utterance that was previously submitted for transcription by a production speech recognizer. The production speech recognizer uses initial production speech recognizer components in generating transcriptions of speech data items. A transcription for each speech data item is generated using an offline speech recognizer, and the offline speech recognizer components are configured to improve speech recognition accuracy in comparison with the initial production speech recognizer components. The updated production speech recognizer components are trained for the production speech recognizer using a selected subset of the transcriptions of the speech data items generated by the offline speech recognizer. An updated production speech recognizer component is provided to the production speech recognizer for use in transcribing subsequently received speech data items.

Acoustic model training corpus selection

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a set of training utterances. The methods, systems, and apparatus include actions of obtaining a target multi-dimensional distribution of characteristics in an initial set of candidate utterances and selecting a subset of the initial set of candidate utterances based on speech recognition confidence scores associated with the candidate utterances. Additional actions include selecting a particular candidate utterance from the subset of the initial set of utterances and determining that adding the particular candidate utterance to a set of training utterances reduces a divergence of a multi-dimensional distribution of the characteristics in the set of training utterances from the target multi-dimensional distribution. Further actions include adding the particular candidate utterance to the set of training utterances.

Utterance selection for automated speech recognizer training

The subject matter of this specification can be embodied in, among other things, a method that includes receiving an audio signal and initiating speech recognition tasks by a plurality of speech recognition systems (SRS's). Each SRS is configured to generate a recognition result specifying possible speech included in the audio signal and a confidence value indicating a confidence in a correctness of the speech result. The method also includes completing a portion of the speech recognition tasks including generating one or more recognition results and one or more confidence values for the one or more recognition results, determining whether the one or more confidence values meets a confidence threshold, aborting a remaining portion of the speech recognition tasks for SRS's that have not completed generating a recognition result, and outputting a final recognition result based on at least one of the generated one or more speech results.

Growing community of inventors

Glen Rock, NJ, United States of America

Olivier Siohan