mlsanityData to 7 Oct 2026

TF-GridNet: Making Time-Frequency Domain Models Great Again for Monaural Speaker Separation

arXiv 2209.03952 ↗First posted 8 Sep 2022cs.SD eess.AScited by 48

Not on the map. Why?

Abstract (arXiv)

We propose TF-GridNet, a novel multi-path deep neural network (DNN) operating in the time-frequency (T-F) domain, for monaural talker-independent speaker separation in anechoic conditions. The model stacks several multi-path blocks, each consisting of an intra-frame spectral module, a sub-band temporal module, and a full-band self-attention module, to leverage local and global spectro-temporal information for separation. The model is trained to perform complex spectral mapping, where the real and imaginary (RI) components of the input mixture are stacked as input features to predict target RI components. Besides using the scale-invariant signal-to-distortion ratio (SI-SDR) loss for model training, we include a novel loss term to encourage separated sources to add up to the input mixture. Without using dynamic mixing, we obtain 23.4 dB SI-SDR improvement (SI-SDRi) on the WSJ0-2mix dataset, outperforming the previous best by a large margin.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Sep 2022.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 9; 2024: 10; 2025: 22; 2026: 4.

48 papers.

Sort:

By area:

  1. 2023AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Headcited by 264
  2. 2024State Space Model for New-Generation Network Alternative to Transformers: A Surveycited by 59
  3. 2022Diffusion-based Generative Speech Source Separationcited by 41
  4. 2024A Survey of Mambacited by 39
  5. 2025SepPrune: Structured Pruning for Efficient Deep Speech Separationcited by 31
  6. 2024Annealed Multiple Choice Learning: Overcoming limitations of Winner-takes-all with annealingcited by 12
  7. 2023High-Quality Visually-Guided Sound Separation from Diverse Categoriescited by 11
  8. 2024Look Once to Hear: Target Speech Hearing with Noisy Examplescited by 11
  9. 2024TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separationcited by 10
  10. 2024OmniSep: Unified Omni-Modality Sound Separation with Query-Mixupcited by 8
  11. 2023A Neural State-Space Model Approach to Efficient Speech Separationcited by 6
  12. 2022Speech separation with large-scale self-supervised learningcited by 5
36 more
  1. 2023Multi-Microphone Speaker Separation by Spatial Regionscited by 4
  2. 2023AudioSlots: A slot-centric generative model for audio separationcited by 4
  3. 2025A Study of the Scale Invariant Signal to Distortion Ratio in Speech Separation with Noisy Referencescited by 4
  4. 2025Unifying Diarization, Separation, and ASR with Multi-Speaker Encodercited by 4
  5. 2022MedleyVox: An Evaluation Dataset for Multiple Singing Voices Separationcited by 3
  6. 2023On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environmentscited by 3
  7. 2025A Survey of Deep Learning for Complex Speech Spectrogramscited by 3
  8. 2025EDNet: A Versatile Speech Enhancement Framework with Gating Mamba Mechanism and Phase Shift-Invariant Trainingcited by 3
  9. 2025SenSE: Semantic-Aware High-Fidelity Universal Speech Enhancementcited by 3
  10. 2023RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separationcited by 2
  11. 2024CleanUMamba: A Compact Mamba Network for Speech Denoising using Channel Pruningcited by 2
  12. 2025Contextual Speech Extraction: Leveraging Textual History as an Implicit Cue for Target Speech Extractioncited by 2
  13. 2025Plug-and-Play Co-Occurring Face Attention for Robust Audio-Visual Speaker Extractioncited by 2
  14. 2025Knowing When to Quit: Probabilistic Early Exits for Speech Separationcited by 2
  15. 2025Neural Speech Extraction with Human Feedbackcited by 2
  16. 2025High-Quality Sound Separation Across Diverse Categories via Visually-Guided Generative Modelingcited by 2
  17. 2023Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for Meeting Transcriptioncited by 1
  18. 2024SPMamba: State-space model is all you need in speech separationcited by 1
  19. 2024Speech Boosting: Low-Latency Live Speech Enhancement for TWS Earbudscited by 1
  20. 2025Target Speaker Extraction through Comparing Noisy Positive and Negative Audio Enrollmentscited by 1
  21. 2025Unleashing the Power of Natural Audio Featuring Multiple Sound Sourcescited by 1
  22. 2025Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restorationcited by 1
  23. 2025Time-Frequency-Based Attention Cache Memory Model for Real-Time Speech Separationcited by 1
  24. 2025TF-MLPNet: Tiny Real-Time Neural Speech Separationcited by 1
  25. 2025Error Analysis in a Modular Meeting Transcription Systemcited by 1
  26. 2025Proactive Hearing Assistants that Isolate Egocentric Conversationscited by 1
  27. 2025MamTiff-CAD: Multi-Scale Latent Diffusion with Mamba+ for Complex Parametric Sequencecited by 1
  28. 2026Omni-directional attention mechanism based on Mamba for speech separationcited by 1
  29. 2023Complete and separate: Conditional separation with missing target source attribute completioncited by 0
  30. 2024Improving Real-Time Music Accompaniment Separation with MMDenseNetcited by 0
  31. 2025Causal Self-supervised Pretrained Frontend with Predictive Code for Speech Separationcited by 0
  32. 2025LSZone: A Lightweight Spatial Information Modeling Architecture for Real-time In-car Multi-zone Speech Separationcited by 0
  33. 2025Is Phase Really Needed for Weakly-Supervised Dereverberation ?cited by 0
  34. 2026The Costs of Reproducibility in Music Separation Research: a Replication of Band-Split RNNcited by 0
  35. 2026TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separationcited by 0
  36. 2026DriftSE: Speech Enhancement with Generative Driftingcited by 0