Skip to content

Commit 775ccf8

Browse files
authored
Update README.md
1 parent 3ab1e38 commit 775ccf8

File tree

1 file changed

+16
-3
lines changed

1 file changed

+16
-3
lines changed

README.md

+16-3
Original file line numberDiff line numberDiff line change
@@ -3,15 +3,28 @@
33
This repository for the official PyTorch implementation of [Microphone Array Generalization for Multichannel Narrowband Deep Speech Enhancement](https://arxiv.org/abs/2107.12601), accepted by InterSpeech 2021.
44

55
## Introduction
6-
Our work addresses the problem of microphone array generalization for deep-learning-based end-to-end multichannel speech enhancement. We aim to train a unique potentially performing well on unseen microphone arrays. The goal is to make the network learn the universal information for speech enhancement that is available for any array geometry, rather than learn the one-array-dedicated characteristics. To resolve this problem, a single network is trained using data recorded by various **VIRTUAL** microphone arrays of different geometries using RIR Generator[1] and simulated diffused noise[2]. We design three variants of our recently proposed original NarrowBand Deep Filtering(NBDF) network to cope with the agnostic number of microphones.
6+
Our work addresses the problem of microphone array generalization for deep-learning-based end-to-end multichannel speech enhancement. We aim to train a unique potentially performing well on unseen microphone arrays. The goal is to make the network learn the universal information for speech enhancement that is available for any array geometry, rather than learn the one-array-dedicated characteristics. To resolve this problem, a single network is trained using data recorded by various **VIRTUAL** microphone arrays of different geometries using RIR Generator[1] and simulated diffused noise[2]. We design three variants of our recently proposed original NarrowBand Deep Filtering(NBDF) [3] network to cope with the agnostic number of microphones.
77

88

99
![figure 1](https://github.com/RusselZHANG/Microphone-Array-Generalization-for-Multichannel-Narrowband-Deep-Speech-Enhancement/blob/main/doc/fig.png)
1010

1111
## Key Features
1212
* Simulated_RIR_Generator
13-
* CP-NBDF, CC-NBDF, PW-NBDF network
13+
* Network
14+
* CP-NBDF
15+
* CC-NBDF
16+
* PW-NBDF
1417
* Train
1518
* Inference
1619
* Evaluation
17-
*
20+
21+
## Get started
22+
(1) Clone:
23+
```
24+
$ git clone https://github.com/atomicoo/Tacotron2-PyTorch.git
25+
```
26+
(2) Requirements:
27+
```
28+
$ pip install -r requirements.txt
29+
```
30+

0 commit comments

Comments
 (0)