# SEOFP-NET: Compression and Acceleration of Deep Neural Networks for Speech Enhancement Using Sign-Exponent-Only Floating-Points

arXiv: https://arxiv.org/abs/2111.04436 · HTML: https://mlsanity.com/paper/2111.04436/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 83 references that are in the map.
- First posted on arXiv 8 Nov 2021.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Speech Recognition with Deep Recurrent Neural Networks](https://mlsanity.com/paper/1303.5778/) (2013)
- [BinaryConnect: Training Deep Neural Networks with binary weights during propagations](https://mlsanity.com/paper/1511.00363/) (2015)
- [Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training](https://mlsanity.com/paper/1712.01887/) (2017)
- [Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights](https://mlsanity.com/paper/1702.03044/) (2017)
- [Supervised Speech Separation Based on Deep Learning: An Overview](https://mlsanity.com/paper/1708.07524/) (2017)
- [Compressing Deep Convolutional Networks using Vector Quantization](https://mlsanity.com/paper/1412.6115/) (2014)
- [SEGAN: Speech Enhancement Generative Adversarial Network](https://mlsanity.com/paper/1703.09452/) (2017)
- [ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA](https://mlsanity.com/paper/1612.00694/) (2016)
- [End-to-End Waveform Utterance Enhancement for Direct Evaluation Metrics Optimization by Fully Convolutional Neural Networks](https://mlsanity.com/paper/1709.03658/) (2017)
- [Raw Waveform-based Speech Enhancement by Fully Convolutional Networks](https://mlsanity.com/paper/1703.02205/) (2017)
- [A Differentiable Perceptual Audio Metric Learned from Just Noticeable Differences](https://mlsanity.com/paper/2001.04460/) (2020)
- [Conditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verification](https://mlsanity.com/paper/1709.01703/) (2017)
- [Exploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognition](https://mlsanity.com/paper/1711.05747/) (2017)
- [Multichannel End-to-end Speech Recognition](https://mlsanity.com/paper/1703.04783/) (2017)
- [Complex spectrogram enhancement by convolutional neural network with multi-metrics learning](https://mlsanity.com/paper/1704.08504/) (2017)
- [Dense CNN with Self-Attention for Time-Domain Speech Enhancement](https://mlsanity.com/paper/2009.01941/) (2020)
- [VoiceID Loss: Speech Enhancement for Speaker Verification](https://mlsanity.com/paper/1904.03601/) (2019)
- [On the Compression of Recurrent Neural Networks with an Application to LVCSR acoustic modeling for Embedded Speech Recognition](https://mlsanity.com/paper/1603.08042/) (2016)
- [A Model Compression Method with Matrix Product Operators for Speech Enhancement](https://mlsanity.com/paper/2010.04950/) (2020)
- [Exploring Deep Hybrid Tensor-to-Vector Network Architectures for Regression Based Speech Enhancement](https://mlsanity.com/paper/2007.13024/) (2020)
- [Precision Scaling of Neural Networks for Efficient Audio Processing](https://mlsanity.com/paper/1712.01340/) (2017)
- [Tensor-to-Vector Regression for Multi-channel Speech Enhancement based on Tensor-Train Network](https://mlsanity.com/paper/2002.00544/) (2020)
- [Increasing Compactness Of Deep Learning Based Speech Enhancement Models With Parameter Pruning And Quantization Techniques](https://mlsanity.com/paper/1906.01078/) (2019)
- [Time-domain Speech Enhancement with Generative Adversarial Learning](https://mlsanity.com/paper/2103.16149/) (2021)

## Abstract (arXiv)

Numerous compression and acceleration strategies have achieved outstanding results on classification tasks in various fields, such as computer vision and speech signal processing. Nevertheless, the same strategies have yielded ungratified performance on regression tasks because the nature between these and classification tasks differs. In this paper, a novel sign-exponent-only floating-point network (SEOFP-NET) technique is proposed to compress the model size and accelerate the inference time for speech enhancement, a regression task of speech signal processing. The proposed method compressed the sizes of deep neural network (DNN)-based speech enhancement models by quantizing the fraction bits of single-precision floating-point parameters during training. Before inference implementation, all parameters in the trained SEOFP-NET model are slightly adjusted to accelerate the inference time by replacing the floating-point multiplier with an integer-adder. For generalization, the SEOFP-NET technique is introduced to different speech enhancement tasks in speech signal processing with different model architectures under various corpora. The experimental results indicate that the size of SEOFP-NET models can be significantly compressed by up to 81.249% without noticeably downgrading their speech enhancement performance, and the inference time can be accelerated to 1.212x compared with the baseline models. The results also verify that the proposed SEOFP-NET can cooperate with other efficiency strategies to achieve a synergy effect for model compression. In addition, the just noticeable difference (JND) was applied to the user study experiment to statistically analyze the effect of speech enhancement on listening. The results indicate that the listeners cannot facilely differentiate between the enhanced speech signals processed by the baseline model and the proposed SEOFP-NET.