Neural Network-based Virtual Microphone Estimator

01/12/2021
by   Tsubasa Ochiai, et al.
0

Developing microphone array technologies for a small number of microphones is important due to the constraints of many devices. One direction to address this situation consists of virtually augmenting the number of microphone signals, e.g., based on several physical model assumptions. However, such assumptions are not necessarily met in realistic conditions. In this paper, as an alternative approach, we propose a neural network-based virtual microphone estimator (NN-VME). The NN-VME estimates virtual microphone signals directly in the time domain, by utilizing the precise estimation capability of the recent time-domain neural networks. We adopt a fully supervised learning framework that uses actual observations at the locations of the virtual microphones at training time. Consequently, the NN-VME can be trained using only multi-channel observations and thus directly on real recordings, avoiding the need for unrealistic physical model-based assumptions. Experiments on the CHiME-4 corpus show that the proposed NN-VME achieves high virtual microphone estimation performance even for real recordings and that a beamformer augmented with the NN-VME improves both the speech enhancement and recognition performance.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/06/2017

Achieving the time of 1-NN, but the accuracy of k-NN

We propose a simple approach which, given distributed computing resource...
research
11/18/2020

Multi-Channel Automatic Speech Recognition Using Deep Complex Unet

The front-end module in multi-channel automatic speech recognition (ASR)...
research
06/12/2014

A Cascade Neural Network Architecture investigating Surface Plasmon Polaritons propagation for thin metals in OpenMP

Surface plasmon polaritons (SPPs) confined along metal-dielectric interf...
research
03/04/2020

Foreground model recognition through Neural Networks for CMB B-mode observations

In this work we present a Neural Network (NN) algorithm for the identifi...
research
06/23/2016

NN-grams: Unifying neural network and n-gram language models for Speech Recognition

We present NN-grams, a novel, hybrid language model integrating n-grams ...
research
09/09/2022

Reconstructing the Dynamic Directivity of Unconstrained Speech

An accurate model of natural speech directivity is an important step tow...
research
04/02/2019

Unsupervised training of neural mask-based beamforming

We present an unsupervised training approach for a neural network-based ...

Please sign up or login with your details

Forgot password? Click here to reset