# Asteroid: the PyTorch-based audio source separation toolkit for researchers

arXiv: https://arxiv.org/abs/2005.04132 · HTML: https://mlsanity.com/paper/2005.04132/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 May 2020.

## Built on by (most cited first, 30 of 45)

- [SpeechBrain: A General-Purpose Speech Toolkit](https://mlsanity.com/paper/2106.04624/) (2021)
- [An efficient encoder-decoder architecture with top-down attention for speech separation](https://mlsanity.com/paper/2209.15200/) (2022)
- [MESH2IR: Neural Acoustic Impulse Response Generator for Complex 3D Scenes](https://mlsanity.com/paper/2205.09248/) (2022)
- [ESPnet2-TTS: Extending the Edge of TTS Research](https://mlsanity.com/paper/2110.07840/) (2021)
- [Look Once to Hear: Target Speech Hearing with Noisy Examples](https://mlsanity.com/paper/2405.06289/) (2024)
- [Test-Time Adaptation Toward Personalized Speech Enhancement: Zero-Shot Learning with Knowledge Distillation](https://mlsanity.com/paper/2105.03544/) (2021)
- [An Audio-Visual Speech Separation Model Inspired by Cortico-Thalamo-Cortical Circuits](https://mlsanity.com/paper/2212.10744/) (2022)
- [ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding](https://mlsanity.com/paper/2207.09514/) (2022)
- [USTC-NELSLIP System Description for DIHARD-III Challenge](https://mlsanity.com/paper/2103.10661/) (2021)
- [Multimodal Emotion Recognition with Modality-Pairwise Unsupervised Contrastive Loss](https://mlsanity.com/paper/2207.11482/) (2022)
- [End-to-End Complex-Valued Multidilated Convolutional Neural Network for Joint Acoustic Echo Cancellation and Noise Suppression](https://mlsanity.com/paper/2110.00745/) (2021)
- [Zero-Shot Duet Singing Voices Separation with Diffusion Models](https://mlsanity.com/paper/2311.07345/) (2023)
- [Efficient Personalized Speech Enhancement through Self-Supervised Learning](https://mlsanity.com/paper/2104.02017/) (2021)
- [Directed Speech Separation for Automatic Speech Recognition of Long Form Conversational Speech](https://mlsanity.com/paper/2112.05863/) (2021)
- [SynthSOD: Developing an Heterogeneous Dataset for Orchestra Music Source Separation](https://mlsanity.com/paper/2409.10995/) (2024)
- [BLOOM-Net: Blockwise Optimization for Masking Networks Toward Scalable and Efficient Speech Enhancement](https://mlsanity.com/paper/2111.09372/) (2021)
- [Disentangling the Impacts of Language and Channel Variability on Speech Separation Networks](https://mlsanity.com/paper/2203.16040/) (2022)
- [On Neural Architectures for Deep Learning-based Source Separation of Co-Channel OFDM Signals](https://mlsanity.com/paper/2303.06438/) (2023)
- [Tune-In: Training Under Negative Environments with Interference for Attention Networks Simulating Cocktail Party Effect](https://mlsanity.com/paper/2103.01461/) (2021)
- [A Multimodal Data-driven Framework for Anxiety Screening](https://mlsanity.com/paper/2303.09041/) (2023)
- [End-to-End Integration of Speech Separation and Voice Activity Detection for Low-Latency Diarization of Telephone Conversations](https://mlsanity.com/paper/2303.12002/) (2023)
- [Online speaker diarization of meetings guided by speech separation](https://mlsanity.com/paper/2402.00067/) (2024)
- [Score-informed Music Source Separation: Improving Synthetic-to-real Generalization in Classical Music](https://mlsanity.com/paper/2503.07352/) (2025)
- [Whispering Under the Eaves: Protecting User Privacy Against Commercial and LLM-powered Automatic Speech Recognition Systems](https://mlsanity.com/paper/2504.00858/) (2025)
- [Deep Learning Tools for Audacity: Helping Researchers Expand the Artist's Toolkit](https://mlsanity.com/paper/2110.13323/) (2021)
- [Learning Filterbanks for End-to-End Acoustic Beamforming](https://mlsanity.com/paper/2111.04614/) (2021)
- [Analysis of impact of emotions on target speech extraction and speech separation](https://mlsanity.com/paper/2208.07091/) (2022)
- [Papez: Resource-Efficient Speech Separation with Auditory Working Memory](https://mlsanity.com/paper/2407.00888/) (2024)
- [SonicSieve: Bringing Directional Speech Extraction to Smartphones Using Acoustic Microstructures](https://mlsanity.com/paper/2504.10793/) (2025)
- [Frequency-Weighted Training Losses for Phoneme-Level DNN-based Speech Enhancement](https://mlsanity.com/paper/2506.18714/) (2025)

## Abstract (arXiv)

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 .