Patent · US Active

Hidden markov model for speech processing with training method

US9020816B2 · kind B2 · utility

6Cited by
90References
27Claims
0Family size

Assignee

Inventor

Key dates

Filing dateAug 13, 2009
Grant dateApr 28, 2015
Priority date
Expiry dateJul 26, 2032

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L25/24
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A method, system and apparatus are shown for identifying non-language speech sounds in a speech or audio signal. An audio signal is segmented and feature vectors are extracted from the segments of the audio signal. The segment is classified using a hidden Markov model (HMM) that has been trained on sequences of these feature vectors. Post-processing components can be utilized to enhance classification. An embodiment is described in which the hidden Markov model is used to classify a segment as a language speech sound or one of a variety of non-language speech sounds. Another embodiment is described in which the hidden Markov model is trained using discriminative learning.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.