Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Conferences, Workshops, Symposiums, and Seminars
  4. Accent adaptation using Subspace Gaussian Mixture Models
 
conference paper

Accent adaptation using Subspace Gaussian Mixture Models

Motlicek, Petr
•
Garner, Philip N.
•
Kim, Namhoon
Show more
2013
2013 IEEE International Conference on Acoustics, Speech and Signal Processing
IEEE - The 38th International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

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.

  • Files
  • Details
  • Metrics
Loading...
Thumbnail Image
Name

Motlicek_ICASSP2013-2_2013.pdf

Access type

openaccess

Size

87.18 KB

Format

Adobe PDF

Checksum (MD5)

e1c148ccc46811ce1b2a73cbdfa6bf10

Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés