Frequency Domain Multi-channel Acoustic Modeling For Distant Speech Recognition
2019 · Minhua Wu, Kenichi Kumatani, Shiva Sundaram, et al.
Abstract
Conventional far-field automatic speech recognition (ASR) systems typically employ microphone array techniques for speech enhancement in order to improve robustness against noise or reverberation. However, such speech enhancement techniques do not always yield ASR accuracy improvement because the optimization criterion for speech enhancement is not directly relevant to the ASR objective. In this work, we develop new acoustic modeling techniques that optimize spatial filtering and long short-term memory (LSTM) layers from multi-channel (MC) input based on an ASR criterion directly. In contrast to conventional methods, we incorporate array processing knowledge into the acoustic model. Moreover, we initialize the network with beamformers' coefficients. We investigate effects of such MC neural networks through ASR experiments on the real-world far-field data where users are interacting with an ASR system in uncontrolled acoustic environments. We show that our MC acoustic model can reduce a
Authors
(none)
Tags
Stats
Related papers
- Multi-geometry Spatial Acoustic Modeling For Distant Speech Recognition (2019)6.34
- 3-D Feature And Acoustic Modeling For Far-field Speech Recognition (2019)0.00
- Leveraging Redundancy In Multiple Audio Signals For Far-field Speech Recognition (2023)0.00
- Automatic Channel Selection And Spatial Feature Integration For Multi-channel Speech Recognition Across Various Array Topologies (2023)8.09
- Improved Frequency Modulation Features For Multichannel Distant Speech Recognition (2018)6.77
- A Unified Multichannel Far-field Speech Recognition System: Combining Neural Beamforming With Attention Based End-to-end Model (2024)0.00
- A Network Of Deep Neural Networks For Distant Speech Recognition (2017)10.35
- Deep Long Short-term Memory Adaptive Beamforming Networks For Multichannel Robust Speech Recognition (2017)13.23