Affordable Access

Cognitive componets of speech at different time scales

Authors
Publication Date
Keywords
  • Cognitive Component Analysis (Coca) Is Defined As Unsupervised Grouping Of Data Leading To A Group S
  • We Focus Here On Speech At Different Time Scales Looking For Possible Hidden ‘Cognitive Structure’
  • Statistical Regularities Have Earlier Been Revealed At Multiple Time Scales Corresponding To: Phonem
  • Gender
  • Height And Speaker Identity
  • We Here Show That The Same Simple Unsupervised Learning Algorithm Can Detect These Cues
  • Our Basic Features Are 25-Dimensional Short Time Mel-Frequency Weighted Cepstral Coefficients
  • Assumed To Model The Basic Representation Of The Human Auditory System
  • The Basic Features Are Aggregated In Time To Obtain Features At Longer Time Scales
  • Simple Energy Based Filtering Is Used To Achieve A Sparse Representation
  • Our Hypothesis Is Now Basically Ecological: We Hypothesize That Features That Are Essentially Indepe
  • The Representations Are Indeed Shown To Be Very Similar Between Supervised Learning (Invoking Cognit
  • Hence Lending Additional Support To Our Cognitive Component Hypothesis

Abstract

Cognitive componets of speech at different time scales - DTU Orbit (16/02/14) Feng, Ling; Hansen, Lars Kai / Cognitive componets of speech at different time scales. Twenty-Ninth Meeting of the Cognitive Science Society (CogSci'07). 2007. p. 983-988. Publication: Research - peer-review › Article in proceedings – Annual report year: 2007

There are no comments yet on this publication. Be the first to share your thoughts.