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

arXiv: https://arxiv.org/abs/1711.08016 · HTML: https://mlsanity.com/paper/1711.08016/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2017.

## Built on by (most cited first, 10 of 10)

- [A Survey of Sound Source Localization with Deep Learning Methods](https://mlsanity.com/paper/2109.03465/) (2021)
- [Internal Language Model Training for Domain-Adaptive End-to-End Speech Recognition](https://mlsanity.com/paper/2102.01380/) (2021)
- [Minimum Word Error Rate Training with Language Model Fusion for End-to-End Speech Recognition](https://mlsanity.com/paper/2106.02302/) (2021)
- [End-to-End Multi-Channel Transformer for Speech Recognition](https://mlsanity.com/paper/2102.03951/) (2021)
- [Internal Language Model Adaptation with Text-Only Data for End-to-End Speech Recognition](https://mlsanity.com/paper/2110.05354/) (2021)
- [Improving Noise Robustness of Contrastive Speech Representation Learning with Speech Reconstruction](https://mlsanity.com/paper/2110.15430/) (2021)
- [Multi-Channel Transformer Transducer for Speech Recognition](https://mlsanity.com/paper/2108.12953/) (2021)
- [NASTAR: Noise Adaptive Speech Enhancement with Target-Conditional Resampling](https://mlsanity.com/paper/2206.09058/) (2022)
- [D4AM: A General Denoising Framework for Downstream Acoustic Models](https://mlsanity.com/paper/2311.16595/) (2023)
- [Challenges and Opportunities in Multi-device Speech Processing](https://mlsanity.com/paper/2206.15432/) (2022)

## Abstract (arXiv)

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.