Deep neural factorization for speech recognition

Jen-Tzung Chien, Chen Shen

Research output: Contribution to journalConference articlepeer-review

2 Scopus citations

Abstract

Conventional speech recognition system is constructed by unfolding the spectral-temporal input matrices into one-way vectors and using these vectors to estimate the affine parameters of neural network according to the vector-based error backpropagation algorithm. System performance is constrained because the contextual correlations in frequency and time horizons are disregarded and the spectral and temporal factors are excluded. This paper proposes a spectral-temporal factorized neural network (STFNN) to tackle this weakness. The spectral-temporal structure is preserved and factorized in hidden layers through two ways of factor matrices which are trained by using the factorized error backpropagation. Affine transformation in standard neural network is generalized to the spectro-temporal factorization in STFNN. The structural features or patterns are extracted and forwarded towards the softmax outputs. A deep neural factorization is built by cascading a number of factorization layers with fully-connected layers for speech recognition. An orthogonal constraint is imposed in factor matrices for redundancy reduction. Experimental results show the merit of integrating the factorized features in deep feedforward and recurrent neural networks for speech recognition.

Original languageEnglish
Pages (from-to)3682-3686
Number of pages5
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume2017-August
DOIs
StatePublished - 1 Jan 2017
Event18th Annual Conference of the International Speech Communication Association, INTERSPEECH 2017 - Stockholm, Sweden
Duration: 20 Aug 201724 Aug 2017

Keywords

  • Deep neural network
  • Factorized error backpropagation
  • Spectro-temporal factorization
  • Speech recognition

Fingerprint Dive into the research topics of 'Deep neural factorization for speech recognition'. Together they form a unique fingerprint.

Cite this