mlsanityData to 7 Oct 2026

Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation

arXiv 1910.06379 ↗First posted 14 Oct 2019eess.AS cs.LG cs.SDcited by 182

Not on the map. Why?

Abstract (arXiv)

Recent studies in deep learning-based speech separation have proven the superiority of time-domain approaches to conventional time-frequency-based methods. Unlike the time-frequency domain approaches, the time-domain separation systems often receive input sequences consisting of a huge number of time steps, which introduces challenges for modeling extremely long sequences. Conventional recurrent neural networks (RNNs) are not effective for modeling such long sequences due to optimization difficulties, while one-dimensional convolutional neural networks (1-D CNNs) cannot perform utterance-level sequence modeling when its receptive field is smaller than the sequence length. In this paper, we propose dual-path recurrent neural network (DPRNN), a simple yet effective method for organizing RNN layers in a deep structure to model extremely long sequences. DPRNN splits the long sequential input into smaller chunks and applies intra- and inter-chunk operations iteratively, where the input length can be made proportional to the square root of the original sequence length in each operation. Experiments show that by replacing 1-D CNN with DPRNN and apply sample-level modeling in the time-domain audio separation network (TasNet), a new state-of-the-art performance on WSJ0-2mix is achieved with a 20 times smaller model than the previous best system.

Key facts. Cited by 182 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 28; 2022: 27; 2023: 41; 2024: 35; 2025: 31; 2026: 20.

182 papers.

Sort:

By area:

  1. 2021SpeechBrain: A General-Purpose Speech Toolkitcited by 404
  2. 2021Hybrid Spectrogram and Waveform Source Separationcited by 90
  3. 2021LEAF: A Learnable Frontend for Audio Classificationcited by 69
  4. 2022Music Source Separation with Band-split RNNcited by 69
  5. 2024Proactive Detection of Voice Cloning with Localized Watermarkingcited by 67
  6. 2024Open-Source Conversational AI with SpeechBrain 1.0cited by 55
  7. 2023Efficient Neural Music Generationcited by 50
  8. 2023Parallelizing non-linear sequential models over the sequence lengthcited by 45
  9. 2024Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separationcited by 45
  10. 2024MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selectioncited by 40
  11. 2022An efficient encoder-decoder architecture with top-down attention for speech separationcited by 38
  12. 2021TSTNN: Two-stage Transformer based Neural Network for Speech Enhancement in the Time Domaincited by 36
38 more
  1. 2023MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentionscited by 27
  2. 2022MESH2IR: Neural Acoustic Impulse Response Generator for Complex 3D Scenescited by 23
  3. 2022Real-Time Target Sound Extractioncited by 22
  4. 2024Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesiscited by 22
  5. 2022Temporal Modeling Matters: A Novel Temporal Emotional Modeling Approach for Speech Emotion Recognitioncited by 19
  6. 2022End-to-End Integration of Speech Recognition, Speech Enhancement, and Self-Supervised Learning Representationcited by 17
  7. 2022SepIt: Approaching a Single Channel Speech Separation Boundcited by 16
  8. 2021Compute and memory efficient universal sound source separationcited by 15
  9. 2023Towards Long-Term Time-Series Forecasting: Feature, Pattern, and Distributioncited by 15
  10. 2023Separate And Diffuse: Using a Pretrained Diffusion Model for Improving Source Separationcited by 14
  11. 2024Annealed Multiple Choice Learning: Overcoming limitations of Winner-takes-all with annealingcited by 12
  12. 2021Many-Speakers Single Channel Speech Separation with Optimal Permutation Trainingcited by 11
  13. 2021Discretization and Re-synthesis: an alternative method to solve the Cocktail Party Problemcited by 11
  14. 2022Resource-Efficient Separation Transformercited by 11
  15. 2023IIANet: An Intra- and Inter-Modality Attention Network for Audio-Visual Speech Separationcited by 11
  16. 2024Look Once to Hear: Target Speech Hearing with Noisy Examplescited by 11
  17. 2021Sandglasset: A Light Multi-Granularity Self-attentive Network For Time-Domain Speech Separationcited by 10
  18. 2021VarArray: Array-Geometry-Agnostic Continuous Speech Separationcited by 10
  19. 2022Efficient Transformer-based Speech Enhancement Using Long Frames and STFT Magnitudescited by 10
  20. 2023Unifying Speech Enhancement and Separation with Gradient Modulation for End-to-End Noise-Robust Speech Separationcited by 10
  21. 2023Investigating the Design Space of Diffusion Models for Speech Enhancementcited by 10
  22. 2024TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separationcited by 10
  23. 2022An Audio-Visual Speech Separation Model Inspired by Cortico-Thalamo-Cortical Circuitscited by 9
  24. 2024Noise-robust Speech Separation with Fast Generative Correctioncited by 9
  25. 2021Effective Low-Cost Time-Domain Audio Separation Using Globally Attentive Locally Recurrent Networkscited by 8
  26. 2021Teacher-Student MixIT for Unsupervised and Semi-supervised Speech Separationcited by 8
  27. 2022ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understandingcited by 8
  28. 2023A Generalized Bandsplit Neural Network for Cinematic Audio Source Separationcited by 8
  29. 2024Diffusion-based Generative Modeling with Discriminative Guidance for Streamable Speech Enhancementcited by 8
  30. 2024OmniSep: Unified Omni-Modality Sound Separation with Query-Mixupcited by 8
  31. 2021REAL-M: Towards Speech Separation on Real Mixturescited by 7
  32. 2023X-SepFormer: End-to-end Speaker Extraction Network with Explicit Optimization on Speaker Confusioncited by 6
  33. 2023A Neural State-Space Model Approach to Efficient Speech Separationcited by 6
  34. 2023Assessing the Generalization Gap of Learning-Based Speech Enhancement Systems in Noisy and Reverberant Environmentscited by 6
  35. 2021Personalized Speech Enhancement through Self-Supervised Data Augmentation and Purificationcited by 5
  36. 2021MIMO Self-attentive RNN Beamformer for Multi-speaker Speech Separationcited by 5
  37. 2021Directed Speech Separation for Automatic Speech Recognition of Long Form Conversational Speechcited by 5
  38. 2022Phase-Aware Deep Speech Enhancement: It's All About The Frame Lengthcited by 5

50 most cited of 182 All 182 (JSON)