Corpus ID: 33518605

Semi-Automatic Calibration for Dereverberation by Spectral Subtraction for Continuous Speech Recognition

  title={Semi-Automatic Calibration for Dereverberation by Spectral Subtraction for Continuous Speech Recognition},
  author={K. Riedhammer and T. Bocklet and J. R. Orozco-Arroyave and E. N{\"o}th},
  booktitle={ITG Symposium on Speech Communication},
  • K. Riedhammer, T. Bocklet, +1 author E. Nöth
  • Published in
    ITG Symposium on Speech…
  • Computer Science
  • In this article, we describe a semi-automatic calibration algorithm for dereverberation by spectral subtraction. We verify the method by a comparison to a manual calibration derived from measured room impulse responses (RIR). We conduct extensive experiments to understand the effect of all involved parameters and to verify values suggested in the literature. The experiments are performed on a text read by 31 speakers and recorded by a headset and three far-field microphones. Results are… CONTINUE READING


    Model-based dereverberation of speech in the mel-spectral domain
    • 4
    Clap your hands! Calibrating spectral subtraction for dereverberation
    • 4
    • PDF
    A New Method Based on Spectral Subtraction for Speech
    • 42
    • Highly Influential
    • PDF
    A new feature analysis method for robust ASR in reverberant environments based on the harmonic structure of speech
    • 10
    • PDF
    Verbmobil: Foundations of Speech-to-Speech Translation
    • 747
    • PDF
    Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains
    • J. Gauvain, C. Lee
    • Mathematics, Computer Science
    • IEEE Trans. Speech Audio Process.
    • 1994
    • 2,445
    • PDF
    Transfer-Function Measurement with Maximum-Length Sequences
    • 454