Min Tang

US Patent:

20220383887, Dec 1, 2022

Filed:

May 26, 2021

Appl. No.:

17/331448

Inventors:

- Redmond WA, US
Sefik Emre ESKIMEZ - Bellevue WA, US
Min TANG - Yarrow Point WA, US
Hemin YANG - Bellevue WA, US
Zirun ZHU - Bellevue WA, US
Zhuo CHEN - Woodinville WA, US
Huaming WANG - Clyde Hill WA, US
Takuya YOSHIOKA - Bellevue WA, US

International Classification:

G10L 21/0208
G10L 25/30
G10L 25/51
G06N 3/08

Abstract:

Systems and methods are provided for generating and operating a speech enhancement model optimized for generating noise-suppressed speech outputs for improved human listening and live captioning. A computing system obtains a speech enhancement model trained on a first training dataset to generate noise-suppressed speech outputs and an automatic speech recognition model trained on a second training dataset to generate transcription labels for spoken language utterances. A third training dataset comprising a set of spoken language utterances is applied to the speech enhancement model to obtain a first noise-suppressed speech output which is applied to the automatic speech recognition model to generate a noise-suppressed transcription output for the set of spoken language utterances. Speech enhancement model parameters are updated to optimize the speech enhancement model to generate optimized noise-suppressed speech outputs based on a comparison of the noise-suppressed transcription output and ground truth transcription labels.

US Patent:

20200312324, Oct 1, 2020

Filed:

Mar 26, 2020

Appl. No.:

16/830638

Inventors:

- Burlington MA, US
Min Tang - Yarrow Point WA, US

International Classification:

G10L 15/22
G10L 15/02
G10L 15/30
G10L 15/16
G10L 15/18
G06N 3/08

Abstract:

A method for selecting a speech recognition result on a computing device includes receiving a first speech recognition result determined by the computing device, receiving first features, at least some of the features being determined using the first speech recognition result, determining whether to select the first speech recognition result or to wait for a second speech recognition result determined by a cloud computing service based at least in part on the first speech recognition result and the first features.

US Patent:

20180239755, Aug 23, 2018

Filed:

Feb 20, 2018

Appl. No.:

15/899389

Inventors:

- Bellevue WA, US
Min TANG - Bellevue WA, US

Assignee:

VOICEBOX TECHNOLOGIES CORPORATION - Bellevue WA

International Classification:

G06F 17/28
G10L 15/18
G06F 17/27
G10L 15/02

Abstract:

The invention relates to a system and method for integrating domain information into state transitions of a Finite State Transducer (“FST”) for natural language processing. A system may integrate semantic parsing and information retrieval from an information domain to generate an FST parser that represents the information domain. The FST parser may include a plurality of FST paths, at least one of which may be used to generate a meaning representation from a natural language input. As such, the system may perform domain-based semantic parsing of a natural language input, generating more robust meaning representations using domain information. The system may be applied to a wide range of natural language applications that use natural language input from a user such as, for example, natural language interfaces to computing systems, communication with robots in natural language, personalized digital assistants, question-answer query systems, and/or other natural language processing applications.

US Patent:

20160188573, Jun 30, 2016

Filed:

Sep 15, 2015

Appl. No.:

14/855346

Inventors:

- BELLEVUE WA, US
Min TANG - BELLEVUE WA, US

Assignee:

VOICEBOX TECHNOLOGIES CORPORATION - BELLEVUE WA

International Classification:

G06F 17/28
G10L 15/18
G06F 17/27

Abstract:

The invention relates to a system and method for integrating domain information into state transitions of a Finite State Transducer (“FST”) for natural language processing. A system may integrate semantic parsing and information retrieval from an information domain to generate an FST parser that represents the information domain. The FST parser may include a plurality of FST paths, at least one of which may be used to generate a meaning representation from a natural language input. As such, the system may perform domain-based semantic parsing of a natural language input, generating more robust meaning representations using domain information. The system may be applied to a wide range of natural language applications that use natural language input from a user such as, for example, natural language interfaces to computing systems, communication with robots in natural language, personalized digital assistants, question-answer query systems, and/or other natural language processing applications.

US Patent:

20140278409, Sep 18, 2014

Filed:

May 28, 2014

Appl. No.:

14/288793

Inventors:

- Atlanta GA, US
Yucel Saygin - Instanbul, TR
Min Tang - Redmond WA, US
Gokhan Tur - Los Altos CA, US

Assignee:

AT&T Intellectual Property II, L.P. - Atlanta GA

International Classification:

G10L 15/26

US Classification:

704235

Abstract:

An apparatus and a method for preserving privacy in natural language databases are provided. Natural language input may be received. At least one of sanitizing or anonymizing the natural language input may be performed to form a clean output. The clean output may be stored.