logo Idiap Research Institute        
 [BibTeX] [Marc21]
ACCENT ADAPTATION USING SUBSPACE GAUSSIAN MIXTURE MODELS
Type of publication: Conference paper
Citation: Motlicek_ICASSP2013-2_2013
Publication status: Published
Booktitle: The 38th International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
Year: 2013
Month: May
Pages: 7170-7174
Location: Vancouver, BC, Canada
Organization: IEEE
ISSN: 1520-6149
Crossref: Motlicek_Idiap-RR-38-2013:
DOI: 10.1109/ICASSP.2013.6639054
Abstract: This paper investigates employment of Subspace Gaussian Mixture Models (SGMMs) for acoustic model adaptation towards different accents for English speech recognition. The SGMMs comprise globally-shared and state-specific parameters which can efficiently be employed for various kinds of acoustic parameter tying. Research results indicate that well-defined sharing of acoustic model parameters in SGMMs can significantly outperform adapted systems based on conventional HMM/GMMs. Furthermore, SGMMs rapidly achieve target acoustic models with small amounts of data. Experiments performed with US and UK English versions of the Wall Street Journal (WSJ) corpora indicate that SGMMs lead to approximately 20% and 8% relative improvements with respect to speaker-independent and speaker-adapted acoustic models respectively over conventional HMM/GMMs. Finally, we demonstrate that SGMMs adapted only with 1.5 hours can reach performance of HMM/GMMs trained with 18 hours.
Keywords:
Projects Idiap
SAMSUNG
Authors Motlicek, Petr
Garner, Philip N.
Kim, Namhoon
Cho, Jeongmi
Added by: [UNK]
Total mark: 0
Attachments
  • Motlicek_ICASSP2013-2_2013.pdf
Notes