Neural Network Adaptive Beamforming for Robust Multichannel Speech Recognition

By Bo Li, Tara N. Sainath, Ron J. Weiss, Kevin Wilson, Michiel Bacchiani. 2016

117 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Mechanics, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Mechanics

In Signal Processing

Citations in the corpus

Exploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognition (2017, background): “They are crucial components, either explicitly [3] or implicitly [4, 5], in ASR systems for noise robustness.”
Deep Learning for Audio Signal Processing (2019, background): “They are crucial components, either explicitly [129] or implicitly [130], [131], in ASR systems for noise robustness.”
An Investigation into the Effectiveness of Enhancement in ASR Training and Test for Chime-5 Dinner Party Transcription (2019, background): “Previous studies have shown the benefit of training an ASR on matching enhanced speech [6,7] or on jointly training the enhancement and the acoustic model [8].”
FaSNet: Low-Latency Adaptive Beamforming for Multi-Microphone Audio Processing (2019, methodology): “As shown in [4], the use of the context window incorporates the estimation of cross-microphone delay into the learning process of h it .”
Attention-based Neural Beamforming Layers for Multi-channel Speech Recognition (2021, methodology): “Various neural adaptive beamforming techniques were applied to estimate masks for speech and noise and also to predict beamforming filter coefficients [4, 5, 6].”
Deep Learning for Environmentally Robust Speech Recognition (2017, background): “…beamformers can be generally categorised into two types (Ochiai et al. 2017): (i) beamformers with a mask estimation network (Heymann et al. 2015, 2016a, 2016b; Menne et al. 2016) and (ii) beamformers with a filter estimation network (Li et al. 2016; Meng et al. 2017; Xiao et al. 2016a).”
An unsupervised deep domain adaptation approach for robust speech recognition (2017, methodology): “In [50] , an MTL approach is proposed to simultaneously predict the class label and the clean speech from the noisy speech input.”
A Study of Learning Based Beamforming Methods for Speech Recognition (2016, methodology): “In [6], long short-term memory (LSTM) networks are used to predict the beamforming weights in the time domain directly which has less number of free parameters than the frequency domain.”
Supervised Speech Separation Based on Deep Learning: An Overview (2017, unknown): “[108] employed a deep network to predict spatial filters from array inputs of noisy speech for adaptive beamforming.”
Multichannel Signal Processing With Deep Neural Networks for Automatic Speech Recognition (2017, methodology): “To address the limited adaptability and reduce the computational complexity of the models from [16], [26], we propose a neural network adaptive beamforming (NAB) model [30] which re-estimates a set of spatial filter coefficients at each input frame using a neural network.”