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

arXiv: https://arxiv.org/abs/2209.03952 · HTML: https://mlsanity.com/paper/2209.03952/

## Key facts

- Cited by 48 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Sep 2022.

## Built on by (most cited first, 30 of 48)

- [AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head](https://mlsanity.com/paper/2304.12995/) (2023)
- [State Space Model for New-Generation Network Alternative to Transformers: A Survey](https://mlsanity.com/paper/2404.09516/) (2024)
- [Diffusion-based Generative Speech Source Separation](https://mlsanity.com/paper/2210.17327/) (2022)
- [A Survey of Mamba](https://mlsanity.com/paper/2408.01129/) (2024)
- [SepPrune: Structured Pruning for Efficient Deep Speech Separation](https://mlsanity.com/paper/2505.12079/) (2025)
- [Annealed Multiple Choice Learning: Overcoming limitations of Winner-takes-all with annealing](https://mlsanity.com/paper/2407.15580/) (2024)
- [High-Quality Visually-Guided Sound Separation from Diverse Categories](https://mlsanity.com/paper/2308.00122/) (2023)
- [Look Once to Hear: Target Speech Hearing with Noisy Examples](https://mlsanity.com/paper/2405.06289/) (2024)
- [TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation](https://mlsanity.com/paper/2410.01469/) (2024)
- [OmniSep: Unified Omni-Modality Sound Separation with Query-Mixup](https://mlsanity.com/paper/2410.21269/) (2024)
- [A Neural State-Space Model Approach to Efficient Speech Separation](https://mlsanity.com/paper/2305.16932/) (2023)
- [Speech separation with large-scale self-supervised learning](https://mlsanity.com/paper/2211.05172/) (2022)
- [AudioSlots: A slot-centric generative model for audio separation](https://mlsanity.com/paper/2305.05591/) (2023)
- [Unifying Diarization, Separation, and ASR with Multi-Speaker Encoder](https://mlsanity.com/paper/2508.20474/) (2025)
- [Multi-Microphone Speaker Separation by Spatial Regions](https://mlsanity.com/paper/2303.07143/) (2023)
- [A Study of the Scale Invariant Signal to Distortion Ratio in Speech Separation with Noisy References](https://mlsanity.com/paper/2508.14623/) (2025)
- [MedleyVox: An Evaluation Dataset for Multiple Singing Voices Separation](https://mlsanity.com/paper/2211.07302/) (2022)
- [On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments](https://mlsanity.com/paper/2310.06125/) (2023)
- [A Survey of Deep Learning for Complex Speech Spectrograms](https://mlsanity.com/paper/2505.08694/) (2025)
- [EDNet: A Versatile Speech Enhancement Framework with Gating Mamba Mechanism and Phase Shift-Invariant Training](https://mlsanity.com/paper/2506.16231/) (2025)
- [SenSE: Semantic-Aware High-Fidelity Universal Speech Enhancement](https://mlsanity.com/paper/2509.24708/) (2025)
- [RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation](https://mlsanity.com/paper/2309.17189/) (2023)
- [CleanUMamba: A Compact Mamba Network for Speech Denoising using Channel Pruning](https://mlsanity.com/paper/2410.11062/) (2024)
- [Contextual Speech Extraction: Leveraging Textual History as an Implicit Cue for Target Speech Extraction](https://mlsanity.com/paper/2503.08798/) (2025)
- [Plug-and-Play Co-Occurring Face Attention for Robust Audio-Visual Speaker Extraction](https://mlsanity.com/paper/2505.20635/) (2025)
- [Knowing When to Quit: Probabilistic Early Exits for Speech Separation](https://mlsanity.com/paper/2507.09768/) (2025)
- [Neural Speech Extraction with Human Feedback](https://mlsanity.com/paper/2508.03041/) (2025)
- [High-Quality Sound Separation Across Diverse Categories via Visually-Guided Generative Modeling](https://mlsanity.com/paper/2509.22063/) (2025)
- [Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for Meeting Transcription](https://mlsanity.com/paper/2309.08454/) (2023)
- [SPMamba: State-space model is all you need in speech separation](https://mlsanity.com/paper/2404.02063/) (2024)

## 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.