3-D Feature And Acoustic Modeling For Far-field Speech Recognition

Abstract

Automatic speech recognition in multi-channel reverberant conditions is a challenging task. The conventional way of suppressing the reverberation artifacts involves a beamforming based enhancement of the multi-channel speech signal, which is used to extract spectrogram based features for a neural network acoustic model. In this paper, we propose to extract features directly from the multi-channel speech signal using a multi variate autoregressive (MAR) modeling approach, where the correlations among all the three dimensions of time, frequency and channel are exploited. The MAR features are fed to a convolutional neural network (CNN) architecture which performs the joint acoustic modeling on the three dimensions. The 3-D CNN architecture allows the combination of multi-channel features that optimize the speech recognition cost compared to the traditional beamforming models that focus on the enhancement task. Experiments are conducted on the CHiME-3 and REVERB Challenge dataset using mul

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keypurushothaman20193

Related papers

• Frequency Domain Multi-channel Acoustic Modeling For Distant Speech Recognition (2019)9.92
• Automatic Channel Selection And Spatial Feature Integration For Multi-channel Speech Recognition Across Various Array Topologies (2023)8.09
• Deep Long Short-term Memory Adaptive Beamforming Networks For Multichannel Robust Speech Recognition (2017)13.23
• RIR-SF: Room Impulse Response Based Spatial Feature For Target Speech Recognition In Multi-channel Multi-speaker Scenarios (2023)0.00
• Multi-geometry Spatial Acoustic Modeling For Distant Speech Recognition (2019)6.34
• On Combining Features For Single-channel Robust Speech Recognition In Reverberant Environments (2019)0.00
• Ensemble Of Jointly Trained Deep Neural Network-based Acoustic Models For Reverberant Speech Recognition (2016)0.00
• 3D Neural Beamforming For Multi-channel Speech Separation Against Location Uncertainty (2023)0.00