mlsanityData to 7 Oct 2026

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

arXiv 2111.04436 ↗First posted 8 Nov 2021cs.SD cs.LG eess.AScited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 83 references that are in the map. First posted on arXiv 8 Nov 2021.

Builds on

29 of 83 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  4. 2014Going Deeper with Convolutionscited by 4,231
  5. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  6. 2013Speech Recognition with Deep Recurrent Neural Networkscited by 666
  7. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 571
  8. 2017Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Trainingcited by 471
  9. 2017Supervised Speech Separation Based on Deep Learning: An Overviewcited by 213
  10. 2017Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weightscited by 211
  11. 2014Compressing Deep Convolutional Networks using Vector Quantizationcited by 189
  12. 2017SEGAN: Speech Enhancement Generative Adversarial Networkcited by 165
17 more
  1. 2016ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGAcited by 50
  2. 2017End-to-End Waveform Utterance Enhancement for Direct Evaluation Metrics Optimization by Fully Convolutional Neural Networkscited by 26
  3. 2017Raw Waveform-based Speech Enhancement by Fully Convolutional Networkscited by 24
  4. 2020A Differentiable Perceptual Audio Metric Learned from Just Noticeable Differencescited by 22
  5. 2017Conditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verificationcited by 19
  6. 2017Exploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognitioncited by 19
  7. 2017Multichannel End-to-end Speech Recognitioncited by 17
  8. 2017Complex spectrogram enhancement by convolutional neural network with multi-metrics learningcited by 17
  9. 2020Dense CNN with Self-Attention for Time-Domain Speech Enhancementcited by 16
  10. 2019VoiceID Loss: Speech Enhancement for Speaker Verificationcited by 10
  11. 2016On the Compression of Recurrent Neural Networks with an Application to LVCSR acoustic modeling for Embedded Speech Recognitioncited by 9
  12. 2020A Model Compression Method with Matrix Product Operators for Speech Enhancementcited by 9
  13. 2020Exploring Deep Hybrid Tensor-to-Vector Network Architectures for Regression Based Speech Enhancementcited by 6
  14. 2017Precision Scaling of Neural Networks for Efficient Audio Processingcited by 3
  15. 2020Tensor-to-Vector Regression for Multi-channel Speech Enhancement based on Tensor-Train Networkcited by 3
  16. 2019Increasing Compactness Of Deep Learning Based Speech Enhancement Models With Parameter Pruning And Quantization Techniquescited by 2
  17. 2021Time-domain Speech Enhancement with Generative Adversarial Learningcited by 2

Built on by

Not cited yet.