Microsoft Technology Licensing, LLC

Sri International

Andreas Stolcke

Xuedong D Huang

Nanshan Zeng

Zhuo Chen

Takuya Yoshioka

Lijuan Qin

Dimitrios Basile Dimitriadis

William Isaac Hinthorn

Elizabeth E Shriberg

Martin Graciarena

Luciana Ferrer

Yun-Cheng Ju

Royi Ronen

Horacio E Franco

Oron Nir

Ashwarya Poddar

Ami Turgman

Edan Hauon

Dilek Zeynep Hakkani-Tur

Gokhan Tur

Malcolm G Slaney

Larry Paul Heck

Sarangarajan Parthasarathy

William Scott Mark

Michael Levit

Gregory Kent Myers

Michael John Wolverton

Nicolas Scheffer

Harry Bratt

Bart Peintner

Neil Yorke-Smith

Norman D Winarsky

Heeyoung Lee

Shuangyu Chang

Geoffrey G Zweig

Jing Zheng

Michael Frandsen

Victor Abrash

Kristin Precoda

Murat Akbacak

Sree Harsha Yella

A computer implemented method processes audio streams recorded during a meeting by a plurality of distributed devices. Operations include performing speech recognition on each audio stream by a corresponding speech recognition system to generate utterance-level posterior probabilities as hypotheses for each audio stream, aligning the hypotheses and formatting them as word confusion networks with associated word-level posteriors probabilities, performing speaker recognition on each audio stream by a speaker identification algorithm that generates a stream of speaker-attributed word hypotheses, formatting speaker hypotheses with associated speaker label posterior probabilities and speaker-attributed hypotheses for each audio stream as a speaker confusion network, aligning the word and speaker confusion networks from all audio streams to each other to merge the posterior probabilities and align word and speaker labels, and creating a best speaker-attributed word transcript by selecting the sequence of word and speaker labels with the highest posterior probabilities.

Speaker attributed transcript generation

A computer implemented method includes receiving audio signals representative of speech via multiple audio streams transmitted from corresponding multiple distributed devices, performing, via a neural network model, continuous speech separation for one or more of the received audio signals having overlapped speech, and providing the separated speech on a fixed number of separate output audio channels.

Processing overlapping speech from distributed devices

A computer implemented method includes receiving information streams on a meeting server from a set of multiple distributed devices included in a meeting, receiving audio signals representative of speech by at least two users in at least two of the information streams, receiving at least one video signal of at least one user in the information streams, associating a specific user with speech in the received audio signals as a function of the received audio and video signals, and generating a transcript of the meeting with an indication of the specific user associated with the speech.

Audio-visual diarization to identify meeting attendees

Methods for speaker role determination and scrubbing identifying information are performed by systems and devices. In speaker role determination, data from an audio or text file is divided into respective portions related to speaking parties. Characteristics classifying the portions of the data for speaking party roles are identified in the portions to generate data sets from the portions corresponding to the speaking party roles and to assign speaking party roles for the data sets. For scrubbing identifying information in data, audio data for speaking parties is processed using speech recognition to generate a text-based representation. Text associated with identifying information is determined based on a set of key words/phrases, and a portion of the text-based representation that includes a part of the text is identified. A segment of audio data that corresponds to the identified portion is replaced with different audio data, and the portion is replaced with different text.

System and method for speaker role determination and scrubbing identifying information

A computer implemented method includes receiving audio streams at a meeting server from two distributed devices that are streaming audio captured during an ad-hoc meeting between at least two users, comparing the received audio streams to determine that the received audio streams are representative of sound from the ad-hoc meeting, generating a meeting instance to process the audio streams in response to the comparing determining that the audio streams are representative of sound from the ad-hoc meeting, and processing the received audio streams to generate a transcript of the ad-hoc meeting.

Distributed device meeting initiation

Systems and methods for providing customized output based on a user preference in a distributed system are provided. In example embodiments, a meeting server or system receives audio streams from a plurality of distributed devices involved in an intelligent meeting. The meeting system identifies a user corresponding to a distributed device of the plurality of distributed devices and determines a preferred language of the user. A transcript from the received audio streams is generated. The meeting system translates the transcript into the preferred language of the user to form a translated transcript. The translated transcript is provided to the distributed device of the user.

Customized output to optimize for user preference in a distributed system

A computer implemented method includes receiving multiple channels of audio from three or more microphones detecting speech from a meeting of multiple users, localizing speech sources to determine an approximate direction of arrival of speech from a user, using a speech unmixing model to select two channels corresponding to a primary and a secondary microphone, and sending the two selected channels to a meeting server for generation of a speaker attributed meeting transcript.

Audio stream processing for distributed device meeting

A computer implemented method includes receiving audio signals representative of speech via multiple audio channels transmitted from corresponding multiple distributed devices, designating one of the audio channels as a reference channel, and for each of the remaining audio channels, determine a difference in time from the reference channel, and correcting each remaining audio channel by compensating for the corresponding difference in time from the reference channel.

Synchronization of audio signals from distributed devices

Prosodic features are used for discriminating computer-directed speech from human-directed speech. Statistics and models describing energy/intensity patterns over time, speech/pause distributions, pitch patterns, vocal effort features, and speech segment duration patterns may be used for prosodic modeling. The prosodic features for at least a portion of an utterance are monitored over a period of time to determine a shape associated with the utterance. A score may be determined to assist in classifying the current utterance as human directed or computer directed without relying on knowledge of preceding utterances or utterances following the current utterance. Outside data may be used for training lexical addressee detection systems for the H-H-C scenario. H-C training data can be obtained from a single-user H-C collection and that H-H speech can be modeled using general conversational speech. H-C and H-H language models may also be adapted using interpolation with small amounts of matched H-H-C data.

Prosodic and lexical addressee detection

Systems and methods are provided for optimizing language models for in-domain applications through an iterative, joint-modeling approach that expresses training material as alternative representations of higher-level tokens, such as named entities and carrier phrases. From a first language model, an in-domain training corpus may be represented as a set of alternative parses of tokens. Statistical information determined from these parsed representations may be used to produce a second (or updated) language model, which is further optimized for the domain. The second language model may be used to determine another alternative parsed representation of the corpus for a next iteration, and the statistical information determined from this representation may be used to produce a third (or further updated) language model. Through each iteration, a language model may be determined that is further optimized for the domain.

Language model optimization for in-domain application

Growing community of inventors

Berkeley, CA, United States of America

Andreas Stolcke