Towards Model Compression for Deep Learning Based Speech Enhancement
- 20 May 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 29 (23299290) , 1785-1794
Abstract
The use of deep neural networks (DNNs) has dramatically elevated the performance of speech enhancement over the last decade. However, to achieve strong enhancement performance typically requires a large DNN, which is both memory and computation consuming, making it difficult to deploy such speech enhancement systems on devices with limited hardware resources or in applications with strict latency requirements. In this study, we propose two compression pipelines to reduce the model size for DNN-based speech enhancement, which incorporates three different techniques: sparse regularization, iterative pruning and clustering-based quantization. We systematically investigate these techniques and evaluate the proposed compression pipelines. Experimental results demonstrate that our approach reduces the sizes of four different models by large margins without significantly sacrificing their enhancement performance. In addition, we find that the proposed approach performs well on speaker separation, which further demonstrates the effectiveness of the approach for compressing speech separation models.Keywords
Funding Information
- National Institute on Deafness and Other Communication Disorders (R01 DC012048)
- Ohio Supercomputer Center
This publication has 34 references indexed in Scilit:
- An Algorithm for Predicting the Intelligibility of Speech Masked by Modulated Noise MaskersIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2016
- Deep clustering: Discriminative embeddings for segmentation and separation2016
- On Training Targets for Supervised Speech SeparationIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2014
- The diverse environments multi-channel acoustic noise database: A database of multichannel environmental noise recordingsThe Journal of the Acoustical Society of America, 2013
- A Sparse-Group LassoJournal of Computational and Graphical Statistics, 2013
- Approximate Nearest Neighbor Search by Residual Vector QuantizationSensors, 2010
- Product Quantization for Nearest Neighbor SearchIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- On Ideal Binary Mask As the Computational Goal of Auditory Scene Analysis2006
- Assessment for automatic speech recognition: II. NOISEX-92: A database and an experiment to study the effect of additive noise on speech recognition systemsSpeech Communication, 1993
- Pruning algorithms-a surveyIEEE Transactions on Neural Networks, 1993