System and method for combining speech recognition outputs from a plurality of domain-specific speech recognizers via machine learning

M Gilbert, S Bangalore, P Haffner, R Bell - US Patent 8,812,321, 2014‏ - Google Patents
Disclosed herein are systems, methods and non-transitory computer-readable media for
performing speech recognition across different applications or environments without model …

System and method for building diverse language models

LDA Barbosa, S Bangalore - US Patent 9,081,760, 2015‏ - Google Patents
Disclosed herein are systems, methods, and non-transitory computer-readable storage
media for collecting web data in order to create diverse language models. A system …

Language model selection for speech-to-text conversion

BM Ballinger, J Schalkwyk, MH Cohen… - US Patent …, 2016‏ - Google Patents
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 …

Automatic language model update

MH Cohen, S Baluja, PJ Moreno - US Patent 7,756,708, 2010‏ - Google Patents
BACKGROUND Speech recognition systems may receive and interpret ver bal input from
users and may take actions based on the input. For example, some users employ speech …

Determining dialog states for language models

P Aleksic, PJM Mengibar - US Patent 9,978,367, 2018‏ - Google Patents
Int. Cl. Systems, methods, devices, and other techniques are c000S S 00S00 (200601)
described herein for determining dialog states that correc000S S 00S00 (200601) spond to …

Language modeling based on spoken and unspeakable corpuses

M Levit, S Chang, B Dumoulin - US Patent 10,192,545, 2019‏ - Google Patents
(Continued) Primary Examiner—Edwin S Leland, III (57) ABSTRACT A computer system for
language modeling may collect training data from one or more information sources …

Socially cognizant translation by detecting and transforming elements of politeness and respect

S Narayanan, P Georgiou - US Patent 8,032,355, 2011‏ - Google Patents
A socially-cognizant translation system that takes social state between speaker and listener
into account when making the translation. The translation may be more formal or less formal …

Multi-modal input on an electronic device

BM Ballinger, J Schalkwyk, MH Cohen… - US Patent …, 2015‏ - Google Patents
(57) ABSTRACT A computer-implemented input-method editor process includes receiving a
request from a user for an application independent input method editor having written and …

Language modeling based on spoken and unspeakable corpuses

M Levit, S Chang, B Dumoulin - US Patent 9,761,220, 2017‏ - Google Patents
Training a language model for use in a speech recognition system typically requires large
quantities of text so that many possible word sequences are observed in the training data …

Generating topic-specific language models

DF Houghton, SM Murray, SV Simon - US Patent 9,892,730, 2018‏ - Google Patents
US9892730B2 - Generating topic-specific language models - Google Patents
US9892730B2 - Generating topic-specific language models - Google Patents Generating …