Investigating Stranded GMM for Improving Automatic Speech Recognition - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2014

Investigating Stranded GMM for Improving Automatic Speech Recognition

Denis Jouvet
Dung Tran
  • Function : Author
  • PersonId : 953494


This paper investigates recently proposed Stranded Gaussian Mixture acoustic Model (SGMM) for Automatic Speech Recognition (ASR). This model extends conventional hidden Markov model (HMM-GMM) by explicitly introducing dependencies between components of the observation Gaussian mixture densities. The main objective of the paper is to experimentally study, how useful SGMM can be for dealing with data, which contains different sources of acoustic variability. First studied sources of variability are age and gender in quiet environment (TIdigits task including child speech). Second, the SGMM modeling is applied on data produced by different speakers and corrupted by non-stationary noise (CHiME 2013 challenge data). Finally, SGMM is applied on the same noisy data, but after performing speech enhancement (i.e., the remaining variability mostly comes from residual noise and different speakers). Although SGMM was originally proposed for robust speech recognition of noisy data, in this work it was found, that the model is more efficient for handling speaker variability in quiet environment.
Fichier principal
Vignette du fichier
ago_HSCMA14_v5.2.pdf (135.78 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01003054 , version 1 (09-06-2014)
hal-01003054 , version 2 (10-06-2014)


  • HAL Id : hal-01003054 , version 2


Arseniy Gorin, Denis Jouvet, Emmanuel Vincent, Dung Tran. Investigating Stranded GMM for Improving Automatic Speech Recognition. 4th Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA 2014), May 2014, Nancy, France. ⟨hal-01003054v2⟩
371 View
344 Download


Gmail Facebook X LinkedIn More