# Beyond Model Size: Redesigning LiSenNet for embedded speech enhancement

arXiv: https://arxiv.org/abs/2609.29866 · HTML: https://mlsanity.com/paper/2609.29866/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 25 references that are in the map.
- First posted on arXiv 24 Sep 2026.

## Builds on (most cited first, 17 of 17)

- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors](https://mlsanity.com/paper/2110.01763/) (2021)
- [NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications](https://mlsanity.com/paper/1804.03230/) (2018)
- [MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement](https://mlsanity.com/paper/2104.03538/) (2021)
- [MobileDets: Searching for Object Detection Architectures for Mobile Accelerators](https://mlsanity.com/paper/2004.14525/) (2020)
- [CMGAN: Conformer-based Metric GAN for Speech Enhancement](https://mlsanity.com/paper/2203.15149/) (2022)
- [TinyLSTMs: Efficient Neural Speech Enhancement for Hearing Aids](https://mlsanity.com/paper/2005.11138/) (2020)
- [DeepFilterNet: A Low Complexity Speech Enhancement Framework for Full-Band Audio based on Deep Filtering](https://mlsanity.com/paper/2110.05588/) (2021)
- [A Hybrid DSP/Deep Learning Approach to Real-Time Full-Band Speech Enhancement](https://mlsanity.com/paper/1709.08243/) (2017)
- [A Perceptually-Motivated Approach for Low-Complexity, Real-Time Enhancement of Fullband Speech](https://mlsanity.com/paper/2008.04259/) (2020)
- [LiSenNet: Lightweight Sub-band and Dual-Path Modeling for Real-Time Speech Enhancement](https://mlsanity.com/paper/2409.13285/) (2024)
- [Weight, Block or Unit? Exploring Sparsity Tradeoffs for Speech Enhancement on Tiny Neural Accelerators](https://mlsanity.com/paper/2111.02351/) (2021)
- [Accelerating RNN-based Speech Enhancement on a Multi-Core MCU with Mixed FP16-INT8 Post-Training Quantization](https://mlsanity.com/paper/2210.07692/) (2022)
- [On the quantization of recurrent neural networks](https://mlsanity.com/paper/2101.05453/) (2021)
- [Scalable Speech Enhancement with Dynamic Channel Pruning](https://mlsanity.com/paper/2412.17121/) (2024)
- [From Diet to Free Lunch: Estimating Auxiliary Signal Properties using Dynamic Pruning Masks in Speech Enhancement Networks](https://mlsanity.com/paper/2602.10666/) (2026)
- [Fast-ULCNet: A fast and ultra low complexity network for single-channel speech enhancement](https://mlsanity.com/paper/2601.14925/) (2026)

## Abstract (arXiv)

Deploying real-time speech enhancement on resource-constrained devices requires meeting strict latency, memory, and energy constraints. Microcontroller NPUs can accelerate neural inference under these constraints, but only through a restricted set of operators in static, integer-quantized graphs. Recent speech-enhancement networks have reduced parameter counts and MACs to levels nominally suitable for microcontrollers, but their operators and execution patterns often remain incompatible with restricted NPUs. We address this gap by redesigning LiSenNet, a 37k parameter sub-band dual-path model, for the STM32N6570-DK Neural-ART accelerator. We replace its recurrent bottleneck with convolutional frequency and temporal mixers, reformulate unsupported operations as static int8-compatible primitives, and use bounded decoder activations to preserve quality after quantization. On VoiceBank-DEMAND, the final NPU-compatible model matches or exceeds the recurrent LiSenNet baseline, reaching PESQ 3.08 versus 3.01 in FP32 and 3.01 versus 2.93 in int8. Deployed on a microcontroller, it processes each 16 ms input hop in 4.83 ms, corresponding to a real-time factor of 0.30. Stateless receptive-field recomputation is an order of magnitude slower at the same frame rate despite higher accelerator utilization. These results show that parameter count and operator compatibility, quantization range, and persistent streaming state must be co-designed to achieve efficient real-time speech enhancement on restricted NPUs.