Investigating Stranded GMM for Improving Automatic Speech Recognition

Arseniy Gorin 1 Denis Jouvet 1 Emmanuel Vincent 1 Dung Tran 1
1 PAROLE - Analysis, perception and recognition of speech
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : 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.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [21 references]  Display  Hide  Download

https://hal.inria.fr/hal-01003054
Contributor : Arseniy Gorin <>
Submitted on : Tuesday, June 10, 2014 - 11:14:08 AM
Last modification on : Thursday, March 21, 2019 - 2:20:42 PM
Document(s) archivé(s) le : Wednesday, September 10, 2014 - 11:30:21 AM

File

ago_HSCMA14_v5.2.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01003054, version 2

Citation

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⟩

Share

Metrics

Record views

608

Files downloads

310