Acoustic hole filling for sparse enrollment data using a cohort universal corpus for speaker recognition.

@article{Suh2012AcousticHF,
  title={Acoustic hole filling for sparse enrollment data using a cohort universal corpus for speaker recognition.},
  author={Jun-Won Suh and John H. L. Hansen},
  journal={The Journal of the Acoustical Society of America},
  year={2012},
  volume={131 2},
  pages={
          1515-28
        }
}
In this study, the problem of sparse enrollment data for in-set versus out-of-set speaker recognition is addressed. The challenge here is that both the training speaker data (5 s) and test material (2~6 s) is of limited test duration. The limited enrollment data result in a sparse acoustic model space for the desired speaker model. The focus of this study is on filling these acoustic holes by harvesting neighbor speaker information to leverage overall system performance. Acoustically similar… CONTINUE READING

Figures, Tables, and Topics from this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 31 REFERENCES

In-Set/Out-of-Set Speaker Recognition Under Sparse Enrollment

  • IEEE Transactions on Audio, Speech, and Language Processing
  • 2007
VIEW 13 EXCERPTS

Rapid speaker adaptation in eigenvoice space

  • IEEE Trans. Speech and Audio Processing
  • 2000
VIEW 18 EXCERPTS
HIGHLY INFLUENTIAL

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

  • IEEE Transactions on Audio, Speech, and Language Processing
  • 2007
VIEW 6 EXCERPTS

Text-independent speaker identification

  • IEEE Signal Processing Magazine
  • 1994
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

FISHER corpus An in-set/out-of-set speaker group is defined from the FISHER corpus

Angkititrakul, Hansen, Prakash
  • J. Acoust. Soc. Am.,
  • 2012
VIEW 2 EXCERPTS

USSS-MITLL 2010 human assisted speaker recognition

  • 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2011
VIEW 1 EXCERPT