Robust Raw Waveform Speech Recognition Using Relevance Weighted Representations

Abstract

Speech recognition in noisy and channel distorted scenarios is often challenging as the current acoustic modeling schemes are not adaptive to the changes in the signal distribution in the presence of noise. In this work, we develop a novel acoustic modeling framework for noise robust speech recognition based on relevance weighting mechanism. The relevance weighting is achieved using a sub-network approach that performs feature selection. A relevance sub-network is applied on the output of first layer of a convolutional network model operating on raw speech signals while a second relevance sub-network is applied on the second convolutional layer output. The relevance weights for the first layer correspond to an acoustic filterbank selection while the relevance weights in the second layer perform modulation filter selection. The model is trained for a speech recognition task on noisy and reverberant speech. The speech recognition experiments on multiple datasets (Aurora-4, CHiME-3, VOiCE

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keyagrawal2020robust

Related papers

• Interpretable Representation Learning For Speech And Audio Signals Based On Relevance Weighting (2020)9.59
• Representation Learning For Speech Recognition Using Feedback Based Relevance Weighting (2021)0.00
• Noise Robust Speech Recognition Using Multi-channel Based Channel Selection And Channelweighting (2016)0.00
• Exploring The Robustness Of Features And Enhancement On Speech Recognition Systems In Highly-reverberant Real Environments (2018)0.00
• A Noise-robust Self-supervised Pre-training Model Based Speech Representation Learning For Automatic Speech Recognition (2022)11.19
• Neural Network-augmented Kalman Filtering For Robust Online Speech Dereverberation In Noisy Reverberant Environments (2022)0.00
• Complementing Handcrafted Features With Raw Waveform Using A Light-weight Auxiliary Model (2021)0.00
• Towards Relevance And Sequence Modeling In Language Recognition (2020)9.23