Disclosed herein are systems, methods and non-transitory computer-readable media for
performing speech recognition across different applications or environments without model …

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 …

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 …

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 …

Abstract Systems, methods, devices, and other techniques are described herein for
determining dialog states that correspond to voice inputs and for biasing a language model …

(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 …

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 …

A computer-implemented input-method editor process includes receiving a request from a
user for an application-independent input method editor having written and spoken input …

A computer system for language modeling may collect training data from one or more
information sources, generate a spoken corpus containing text of transcribed speech, and …

Speech recognition may be improved by generating and using a topic specific language
model. A topic specific language model may be created by performing an initial pass on an …