# It Takes Few to TANGO: A Quantized Distributed Model for Binaural Speech Enhancement

arXiv: https://arxiv.org/abs/2607.08645 · HTML: https://mlsanity.com/paper/2607.08645/

## Key facts

- No citing papers in the map yet (data through 19 Oct 2026).
- Placed in Speech enhancement and noise suppression, one of 11 directions in Speech and audio language models.
- Builds on 9 of its 22 references that are in the map.
- First posted on arXiv 9 Jul 2026.

## Placed in

- Speech and audio language models / [Speech enhancement and noise suppression](https://mlsanity.com/speech/speech-enhancement-and-noise-suppression/)

## Builds on (most cited first, 9 of 9)

- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [TinyLSTMs: Efficient Neural Speech Enhancement for Hearing Aids](https://mlsanity.com/paper/2005.11138/) (2020)
- [DNN-based mask estimation for distributed speech enhancement in spatially unconstrained microphone arrays](https://mlsanity.com/paper/2011.01714/) (2020)
- [Increasing Compactness Of Deep Learning Based Speech Enhancement Models With Parameter Pruning And Quantization Techniques](https://mlsanity.com/paper/1906.01078/) (2019)
- [A study on speech enhancement using exponent-only floating point quantized neural network (EOFP-QNN)](https://mlsanity.com/paper/1808.06474/) (2018)
- [Frequency-Weighted Training Losses for Phoneme-Level DNN-based Speech Enhancement](https://mlsanity.com/paper/2506.18714/) (2025)
- [SEOFP-NET: Compression and Acceleration of Deep Neural Networks for Speech Enhancement Using Sign-Exponent-Only Floating-Points](https://mlsanity.com/paper/2111.04436/) (2021)
- [RT-Tango: Real-Time Distributed Binaural Speech Enhancement for Low-Power Hearing Aid Devices](https://mlsanity.com/paper/2607.01834/) (2026)

## Abstract (arXiv)

Neural network-based multichannel speech enhancement systems achieve strong enhancement performance, but their computational and memory requirements limit deployment on resource-constrained devices. This paper investigates low-precision inference for TANGO, a hybrid distributed binaural speech enhancement system combining neural mask estimation with spatial filtering. We evaluate post-training quantization and quantization-aware training for the neural components, and analyze how quantization errors in the mask estimators propagate through the downstream spatial filtering stage. Our analysis shows that, although quantization degrades intermediate mask estimates, the spatial filtering stage compensates for most quantization-induced errors. Leveraging this robustness, we simplify TANGO into MN-TANGO, reducing both model size and computational complexity while maintaining comparable final performance. By combining INT8 weight-and-activation quantization with ERB compression and grouped recurrent layers, the most compact MN-TANGO reaches 4.65 MMAC/s and 0.177 MB.