Unsupervised training of neural mask-based beamforming

04/02/2019
by   Lukas Drude, et al.
0

We present an unsupervised training approach for a neural network-based mask estimator in an acoustic beamforming application. The network is trained to maximize a likelihood criterion derived from a spatial mixture model of the observations. It is trained from scratch without requiring any parallel data consisting of degraded input and clean training targets. Thus, training can be carried out on real recordings of noisy speech rather than simulated ones. In contrast to previous work on unsupervised training of neural mask estimators, our approach avoids the need for a possibly pre-trained teacher model entirely. We demonstrate the effectiveness of our approach by speech recognition experiments on two different datasets: one mainly deteriorated by noise (CHiME 4) and one by reverberation (REVERB). The results show that the performance of the proposed system is on par with a supervised system using oracle target masks for training and with a system trained using a model-based teacher.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/28/2019

Unsupervised Neural Mask Estimator For Generalized Eigen-Value Beamforming Based ASR

The state-of-art methods for acoustic beamforming in multi-channel ASR a...
research
10/27/2022

A Teacher-student Framework for Unsupervised Speech Enhancement Using Noise Remixing Training and Two-stage Inference

The lack of clean speech is a practical challenge to the development of ...
research
06/19/2018

Speaker Adapted Beamforming for Multi-Channel Automatic Speech Recognition

This paper presents, in the context of multi-channel ASR, a method to ad...
research
01/05/2019

Improving noise robustness of automatic speech recognition via parallel data and teacher-student learning

For real-world speech recognition applications, noise robustness is stil...
research
12/02/2020

Improved MVDR Beamforming Using LSTM Speech Models to Clean Spatial Clustering Masks

Spatial clustering techniques can achieve significant multi-channel nois...
research
02/17/2022

Multi-Channel Speech Denoising for Machine Ears

This work describes a speech denoising system for machine ears that aims...
research
01/12/2021

Neural Network-based Virtual Microphone Estimator

Developing microphone array technologies for a small number of microphon...

Please sign up or login with your details

Forgot password? Click here to reset