Blind estimation of acoustic parameters from speech signals

Current researchers: Mike Brookes, Clement Doire, James Eaton, Alastair H. Moore, Patrick A. Naylor, Pablo Peso Parada

The acoustics of a given room is often characterized by its Acoustic Impulse Response (AIR). Various parameters such as the Reverberation Time (T60) and the Direct-to-Reverberant Ratio (DRR) can be extracted from a measured AIR. These parameters can be used, for example, to predict the quality and intelligibility of speech signals delivered in the room or to improve the robustness of automatic speech recognition systems. Established methods for estimation of the acoustic parameters require knowledge of the AIR.

This project investigates and develops methods for automatic extraction of acoustic parameters from speech signals directly, or non-intrusively, without the need for knowledge of the AIR.

The ACE Challenge to evaluate T60 and DRR estimation algorithms in both fullband and in ISO frequency bands using a range of different talkers, rooms, microphone positions, microphone arrays, and noises recorded in the same rooms is part of the on-going research into this area.

Relevant publications:

  1. J. Eaton, N. D. Gaubitch, A. H. Moore, P. A. Naylor: Proceedings of the ACE Challenge Workshop, a satellite event of IEEE-WASPAA. New Paltz, NY, USA, 2015.
    (2015)
  2. J. Eaton, P. A. Naylor: Direct-to-Reverberant ratio estimation on the ACE corpus using a Two-channel beamformer. In: Proceedings of the ACE Challenge Workshop, a satellite event of IEEE-WASPAA, New Paltz, NY, USA, 2015.
    (2015)
  3. J. Eaton, P. A. Naylor: Reverberation time estimation on the ACE corpus using the SDD method. In: Proceedings of the ACE Challenge Workshop, a satellite event of IEEE-WASPAA, New Paltz, NY, USA, 2015.
    (2015)
  4. J. Eaton, N. D. Gaubitch, A. H. Moore, P. A. Naylor: The ACE Challenge - corpus description and performance evaluation. In: Proc. IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), New Paltz, NY, USA, 2015.
    (2015)
  5. P. Peso Parada, D. Sharma, T. van Waterschoot, P. A. Naylor: Evaluating the Non-intrusive Room Acoustics Algorithm with the ACE Challenge. In: Proceedings of the ACE Challenge Workshop, a satellite event of IEEE-WASPAA, 2015.
    (2015)
  6. J. Eaton, A. H. Moore, P. A. Naylor, J. Skoglund: Direct-to-reverberant ratio estimation using a null-steered beamformer. In: Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP), Brisbane, Australia, 2015.
    (2015)
  7. C. S. J. Doire, M. Brookes, P. A. Naylor, D. Betts, C. M. Hicks, M. A. Dmour, S. Holdt Jensen: Single-Channel Blind Estimation of Reverberation Parameters. In: Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP), Brisbane, Australia, 2015.
    (2015)
  8. J. Y. C. Wen, E. A. P. Habets, P. A. Naylor: Blind estimation of reverberation time based on the distribution of signal decay rates. In: Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP), 2008.
    (2013)
  9. J. Eaton, N. D. Gaubitch, P. A. Naylor: Noise-robust reverberation time estimation using spectral decay distributions with reduced computational cost. In: Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, Canada, 2013.
    (2013)
  10. N. D. Gaubitch, H. W. Löllmann, M. Jeub, T. Falk, P. A. Naylor, P. Vary, M. Brookes: Performance Comparison of Algorithms for Blind Reverberation Time Estimation from Speech. In: Proc. Intl. Workshop Acoust. Signal Enhancement (IWAENC), Aachen, Germany, 2012.
    (2013)