×

Differential acoustic model representation and linear transform-based adaptation for efficient user profile update techniques in automatic speech recognition

  • US 9,406,299 B2
  • Filed: 03/08/2012
  • Issued: 08/02/2016
  • Est. Priority Date: 05/08/2012
  • Status: Active Grant
First Claim
Patent Images

1. A method comprising:

  • adapting, by a computing device, an initial speech recognition acoustic model to produce a speaker adapted acoustic model using speech recognition data from a particular speaker;

    developing, by the computing device, a speaker differential acoustic model representing one or more differences between the initial speech recognition acoustic model and the speaker adapted acoustic model;

    optimizing different quantization ranges for parameter subsets of the speaker adapted acoustic model using a scoring function;

    using the different quantization ranges to minimize an acoustic model difference measure of the speaker adapted acoustic model against the initial speech recognition acoustic model; and

    storing the speaker differential acoustic model for subsequent speech recognition with the particular speaker.

View all claims
  • 4 Assignments
Timeline View
Assignment View
    ×
    ×