Asteroid: the PyTorch-based audio source separation toolkit for researchers
arXiv:2005.04132
Abstract
This paper describes Asteroid, the PyTorch-based audio source separation toolkit for researchers. Inspired by the most successful neural source separation systems, it provides all neural building blocks required to build such a system. To improve reproducibility, Kaldi-style recipes on common audio source separation datasets are also provided. This paper describes the software architecture of Asteroid and its most important features. By showing experimental results obtained with Asteroid's recipes, we show that our implementations are at least on par with most results reported in reference papers. The toolkit is publicly available at https://github.com/mpariente/asteroid .
Submitted to Interspeech 2020
References in corpus (7)
- The NumPy array: a structure for efficient numerical computation
- Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
- Deep attractor network for single-microphone speaker separation
- Two-Step Sound Source Separation: Training on Learned Latent Targets
- The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Speech Quality and Testing Framework
- A Multi-Phase Gammatone Filterbank for Speech Separation via TasNet
- SMS-WSJ: Database, performance measures, and baseline recipe for multi-channel source separation and recognition
Cited by in corpus (11)
- DNN-based mask estimation for distributed speech enhancement in spatially unconstrained microphone arrays
- Efficient Personalized Speech Enhancement through Self-Supervised Learning
- GWA: A Large High-Quality Acoustic Dataset for Audio Processing
- PixIT: Joint Training of Speaker Diarization and Speech Separation from Real-world Multi-speaker Recordings
- End-to-End Complex-Valued Multidilated Convolutional Neural Network for Joint Acoustic Echo Cancellation and Noise Suppression
- Towards Listening to 10 People Simultaneously: An Efficient Permutation Invariant Training of Audio Source Separation Using Sinkhorn's Algorithm
- Exploring the time-domain deep attractor network with two-stream architectures in a reverberant environment
- Causal Signal-Based DCCRN with Overlapped-Frame Prediction for Online Speech Enhancement
- Deep Learning Tools for Audacity: Helping Researchers Expand the Artist's Toolkit
- Manifold-Aware Deep Clustering: Maximizing Angles between Embedding Vectors Based on Regular Simplex
- Refining DNN-based Mask Estimation using CGMM-based EM Algorithm for Multi-channel Noise Reduction