logo Idiap Research Institute        
 [BibTeX] [Marc21]
Analysis of Phone Posterior Feature Space Exploiting Class Specific Sparsity and MLP-based Similarity Measure
Type of publication: Conference paper
Citation: Asaei_ICASSP_2010
Booktitle: 2010 IEEE International Conference on Acoustics, Speech and Signal Processing
Year: 2010
Abstract: Class posterior distributions have recently been used quite successfully in Automatic Speech Recognition (ASR), either for frame or phone level classification or as acoustic features, which can be further exploited (usually after some "ad hoc" transformations) in different classifiers (e.g., in Gaussian Mixture based HMMs). In the present paper, we show preliminary results showing that it may be possible to perform speech recognition without explicit subword unit (phone) classification or likelihood estimation, simply answering the question whether two acoustic (posterior) vectors belong to the same subword unit class or not. In this paper, we first exhibit specific properties of the posterior acoustic space before showing how those properties can be exploited to reach very high performance in deciding (based on an appropriate, trained, distance metric, and hypothesis testing approaches) whether two posterior vectors belong to the same class or not. Performance as high as 90% correct decision rates are reported on the TIMIT database, before reporting kNN phone classification rates.
Keywords:
Projects Idiap
Authors Asaei, Afsaneh
Picart, Benjamin
Bourlard, Hervé
Added by: [UNK]
Total mark: 0
Attachments
  • Asaei_ICASSP_2010.pdf
Notes