Corpus ID: 207794173

The Speed Submission to DIHARD II: Contributions & Lessons Learned

@article{Sahidullah2019TheSS,
  title={The Speed Submission to DIHARD II: Contributions & Lessons Learned},
  author={Md. Sahidullah and Jose Luis Patino and Samuele Cornell and Ruiqing Yin and Sunit Sivasankaran and Herv{\'e} Bredin and Pavel Korshunov and Alessio Brutti and Romain Serizel and Emmanuel Vincent and Nicholas Evans and S{\'e}bastien Marcel and Stefano Squartini and Claude Barras},
  journal={ArXiv},
  year={2019},
  volume={abs/1911.02388}
}
  • Md. Sahidullah, Jose Luis Patino, +11 authors Claude Barras
  • Published in ArXiv 2019
  • Computer Science, Engineering
  • This paper describes the speaker diarization systems developed for the Second DIHARD Speech Diarization Challenge (DIHARD II) by the Speed team. Besides describing the system, which considerably outperformed the challenge baselines, we also focus on the lessons learned from numerous approaches that we tried for single and multi-channel systems. We present several components of our diarization system, including categorization of domains, speech enhancement, speech activity detection, speaker… CONTINUE READING

    Citations

    Publications citing this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 32 REFERENCES

    Speech Denoising with Deep Feature Losses

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Second dihard challenge evaluation plan

    • N. Ryant, K. Church, +4 authors M. Liberman
    • Linguistic Data Consortium, Tech. Rep, 2019.
    • 2019
    VIEW 1 EXCERPT

    Multi-Channel Overlapped Speech Recognition with Location Guided Speech Extraction Network

    VIEW 1 EXCERPT