logo Idiap Research Institute        
 [BibTeX] [Marc21]
Application of Subspace Gaussian Mixture Models in Contrastive Acoustic Scenarios
Type of publication: Idiap-RR
Citation: Motlicek_Idiap-RR-20-2012
Number: Idiap-RR-20-2012
Year: 2012
Month: 7
Institution: Idiap
Address: Rue Marconi 19, Martigny, Switzerland
Abstract: This paper describes experimental results of applying Subspace Gaussian Mixture Models (SGMMs) in two completely diverse acoustic scenarios: (a) for Large Vocabulary Continuous Speech Recognition (LVCSR) task over (well-resourced) English meeting data and, (b) for acoustic modeling of underresourced Afrikaans telephone data. In both cases, the performance of SGMM models is compared with a conventional context-dependent HMM/GMM approach exploiting the same kind of information available during the training. LVCSR systems are evaluated on standard NIST Rich Transcription dataset. For under-resourced Afrikaans, SGMM and HMM/GMM acoustic systems are additionally compared to KL-HMM and multilingual Tandem techniques boosted using supplemental out-of-domain data. Experimental results clearly show that the SGMMapproach (having considerably less model parameters) outperforms conventional HMM/GMM system in both scenarios and for all examined training conditions. In case of under-resourced scenario, the SGMM trained only using indomain data is superior to other tested approaches boosted by data from other domain.
Keywords: acoustic modeling, Automatic Speech Recognition, Subs-ace Gaussian Mixture Models
Projects Idiap
Authors Motlicek, Petr
Garner, Philip N.
Imseng, David
Valente, Fabio
Added by: [ADM]
Total mark: 0
  • Motlicek_Idiap-RR-20-2012.pdf