Onssen: an open-source speech separation and enhancement library

TL;DR

Onssen is an open-source library that facilitates speech separation and enhancement research by providing implementations of various deep learning algorithms, supporting customized datasets, and enabling easy comparison of methods.

Contribution

It introduces a comprehensive, open-source platform for speech separation that supports multiple algorithms and datasets, promoting reproducibility and benchmarking in the field.

Findings

Algorithms in onssen achieve reported performances

Supports most time-frequency mask-based methods

Enables easy comparison across algorithms and datasets

Abstract

Speech separation is an essential task for multi-talker speech recognition. Recently many deep learning approaches are proposed and have been constantly refreshing the state-of-the-art performances. The lack of algorithm implementations limits researchers to use the same dataset for comparison. Building a generic platform can benefit researchers by easily implementing novel separation algorithms and comparing them with the existing ones on customized datasets. We introduce "onssen": an open-source speech separation and enhancement library. onssen is a library mainly for deep learning separation and enhancement algorithms. It uses LibRosa and NumPy libraries for the feature extraction and PyTorch as the back-end for model training. onssen supports most of the Time-Frequency mask-based separation algorithms (e.g. deep clustering, chimera net, chimera++, and so on) and also supports customized datasets. In this paper, we describe the functionality of modules in onssen and show the algorithms implemented by onssen achieve the same performances as reported in the original papers.