TR2017-012

Deep Long Short-Term Memory Adaptive Beamforming Networks for Multichannel Robust Speech Recognition


    •  Meng, Z., Watanabe, S., Hershey, J.R., Erdogan, H., "Deep Long Short-Term Memory Adaptive Beamforming Networks for Multichannel Robust Speech Recognition", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), March 2017.
      BibTeX TR2017-012 PDF
      • @inproceedings{Meng2017mar,
      • author = {Meng, Zhong and Watanabe, Shinji and Hershey, John R. and Erdogan, Hakan},
      • title = {Deep Long Short-Term Memory Adaptive Beamforming Networks for Multichannel Robust Speech Recognition},
      • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
      • year = 2017,
      • month = mar,
      • url = {https://www.merl.com/publications/TR2017-012}
      • }
  • Research Areas:

    Artificial Intelligence, Speech & Audio

Abstract:

Far-field speech recognition in noisy and reverberant conditions remains a challenging problem despite recent deep learning breakthroughs. This problem is commonly addressed by acquiring a speech signal from multiple microphones and performing beamforming over them. In this paper, we propose to use a recurrent neural network with long short-term memory (LSTM) architecture to adaptively estimate real-time beamforming filter coefficients to cope with non-stationary environmental noise and dynamic nature of source and microphones positions which results in a set of timevarying room impulse responses. The LSTM adaptive beamformer is jointly trained with a deep LSTM acoustic model to predict senone labels. Further, we use hidden units in the deep LSTM acoustic model to assist in predicting the beamforming filter coefficients. The proposed system achieves 7.97% absolute gain over baseline systems with no beamforming on CHiME-3 real evaluation set.

 

  • Related News & Events

    •  NEWS    MERL to present 10 papers at ICASSP 2017
      Date: March 5, 2017 - March 9, 2017
      Where: New Orleans
      MERL Contacts: Petros T. Boufounos; Jonathan Le Roux; Dehong Liu; Hassan Mansour; Anthony Vetro; Ye Wang
      Research Areas: Computer Vision, Computational Sensing, Digital Video, Information Security, Speech & Audio
      Brief
      • MERL researchers will presented 10 papers at the upcoming IEEE International Conference on Acoustics, Speech & Signal Processing (ICASSP), to be held in New Orleans from March 5-9, 2017. Topics to be presented include recent advances in speech recognition and audio processing; graph signal processing; computational imaging; and privacy-preserving data analysis.

        ICASSP is the flagship conference of the IEEE Signal Processing Society, and the world's largest and most comprehensive technical conference focused on the research advances and latest technological development in signal and information processing. The event attracts more than 2000 participants each year.
    •