Speaker recognition in noisy conditions with limited training data

@article{McLaughlin2011SpeakerRI,
  title={Speaker recognition in noisy conditions with limited training data},
  author={Niall McLaughlin and Ji Ming and Danny Crookes},
  journal={2011 19th European Signal Processing Conference},
  year={2011},
  pages={1294-1298}
}
In this paper we present a novel method for performing speaker recognition with very limited training data and in the presence of background noise. Similarity-based speaker recognition is considered so that speaker models can be created with limited training speech data. The proposed similarity is a form of cosine similarity used as a distance measure between speech feature vectors. Each speech frame is modelled using subband features, and into this framework, multicondition training and… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-2 OF 2 CITATIONS

References

Publications referenced by this paper.
SHOWING 1-10 OF 18 REFERENCES

The effects of handset variability on speaker recognition performance: experiments on the switchboard corpus

D. A. Reynolds
  • ICASSP-96, vol. 1, pp. 113, 1996.
  • 1996
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Discriminative In-Set/Out-of-Set Speaker Recognition

  • IEEE Transactions on Audio, Speech, and Language Processing
  • 2007
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

A discriminative method for speaker identification with limited data

  • 2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery
  • 2010
VIEW 1 EXCERPT

Robust Speaker Recognition in Noisy Conditions

  • IEEE Transactions on Audio, Speech, and Language Processing
  • 2007
VIEW 2 EXCERPTS

Missing-feature approaches in speech recognition

  • IEEE Signal Processing Magazine
  • 2005
VIEW 1 EXCERPT

Speaker identification in unknown noisy conditions - a universal compensation approach

  • Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.
  • 2005
VIEW 1 EXCERPT

An evaluation of vts and imm for speaker verification in noise

T. Fingscheidt C. Beaugeant Suhadi, S. Stan
  • EUROSPEECH-2003, pp. 1669–1672, 2003.
  • 2003
VIEW 1 EXCERPT