Unlock instant, AI-driven research and patent intelligence for your innovation.

Acoustic model adaptation using geographic information

An acoustic model and geographic technology, applied in digital data processing, natural language data processing, speech analysis, etc., can solve problems such as difficulties in accurately recognizing spoken words, achieve enhanced processing optimization, increase computing efficiency, and improve accuracy Effect

Active Publication Date: 2015-01-14
GOOGLE LLC
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the context of spoken input, automated search recognition ("ASR") engines may have difficulty accurately recognizing spoken words when the sounds associated with a particular language vary based on the user's accent

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Acoustic model adaptation using geographic information
  • Acoustic model adaptation using geographic information
  • Acoustic model adaptation using geographic information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] figure 1 It is a diagram of an example system 100 that uses geo-tagged audio to enhance the accuracy of speech recognition. figure 1 The data flow within the system 100 during states (a) to (i) and the user interface 101 displayed on the mobile device 102 of the system 100 during state (i) are also illustrated. In short, the system 100 adapts one or more acoustic models that are geographically specific to one or more geographic regions. Acoustic models are applied to audio signals geo-annotated with location information to perform speech recognition by comparing the audio signals with statistical representations of sounds that make up each word in a specific language.

[0019] More specifically, the system 100 includes a mobile device 102 that communicates with a server 104 and an ASR engine 105 through one or more networks 106. The server 104 may be a search engine, a dictation engine, a dialogue system, or any other engine or system that uses transcribed speech or call...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for enhancing speech recognition accuracy. In one aspect, a method includes receiving an audio signal that corresponds to an utterance recorded by a mobile device, determining a geographic location associated with the mobile device, adapting one or more acoustic models for the geographic location, and performing speech recognition on the audio signal using the one or more acoustic models model that are adapted for the geographic location.

Description

[0001] Cross references to related applications [0002] This application claims the priority of US Application No. 12 / 787,568 filed on May 26, 2010 entitled ACOUSTIC MODEL ADAPTATION USING GEOGRAPHIC INFORMATION, and the disclosure of which is incorporated herein by reference. Technical field [0003] This manual relates to speech recognition. Background technique [0004] The user of the mobile device can enter text, for example, by typing on a keyboard or dictating into a microphone. In the context of voice input, an automated search recognition ("ASR") engine may have difficulty accurately recognizing spoken words when the sound associated with a particular language changes based on the user's accent. For example, when described by a New Yorker or a Bostonian, a typical ASR engine may recognize the word "park" as the word "pork" or "pack", respectively. Summary of the invention [0005] Generally speaking, an innovative aspect of the subject content described in this specificat...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G10L15/30G10L15/065G06F40/00
CPCG10L15/22G10L15/30G10L15/065
Inventor M·I·洛伊德T·克里斯特詹森
Owner GOOGLE LLC