Online maximum-likelihood mean and variance normalization for speech recognition

Patent metadata

Field	Value
Publication number	US-9280979-B2
Application number	US-201514640912-A
Country	US
Kind code	B2
Filing date	Mar 6, 2015
Priority date	Feb 22, 2010
Publication date	Mar 8, 2016
Grant date	Mar 8, 2016

Abstract

A feature transform for speech recognition is described. An input speech utterance is processed to produce a sequence of representative speech vectors. A time-synchronous speech recognition pass is performed using a decoding search to determine a recognition output corresponding to the speech input. The decoding search includes, for each speech vector after some first threshold number of speech vectors, estimating a feature transform based on the preceding speech vectors in the utterance and partial decoding results of the decoding search. The current speech vector is then adjusted based on the current feature transform, and the adjusted speech vector is used in a current frame of the decoding search.

First claim

What is claimed is:

1. A computer-implemented method for speech recognition comprising:
receiving, from an audio input device, an electric signal corresponding to speech received at the audio input device;
producing a sequence of speech vectors by processing at least a portion of the electric signal that corresponds to a speech utterance of the speech;
performing a single time-synchronous speech recognition pass to determine a recognition output for the speech utterance;
wh…

Assignees

• Nuance Communications Inc

Inventors

• Willett Daniel

Classifications

• G10L15/02 Primary

  Physics · mapped topic

• G10L19/00

  Physics · mapped topic

• G10L19/0212 Primary

  Physics · mapped topic

• G10L15/20

  Physics · mapped topic

• G10L15/34

  Physics · mapped topic