IA-Net : Acceleration and Compression of Speech Enhancement using Integer-adder Deep Neural Network

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review

3 Scopus Citations
View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationProceedings of Interspeech 2019
PublisherInterspeech
Pages1801-1805
ISBN (Electronic)1990-9772
ISBN (Print)2308-457X
Publication statusPublished - Sep 2019

Conference

Title20th Annual Conference of the International Speech Communication Association: Crossroads of Speech and Language (Interspeech 2019)
PlaceAustria
CityGraz
Period15 - 19 September 2019

Abstract

Numerous compression and acceleration techniques achieved state-of-the-art results for classification tasks in speech processing. However, the same techniques produce unsatisfactory performance for regression tasks, because of the different natures of classification and regression tasks. This paper presents a novel integer-adder deep neural network (IA-Net), which compresses model size and accelerates the inference process in speech enhancement, an important task in speech-signal processing, by replacing the floating-point multiplier with an integer-adder. The experimental results show that the inference time of IA-Net can be significantly reduced by 20% and the model size can be compressed by 71.9% without any performance degradation. To the best of our knowledge, this is the first study that decreases the inference time and compresses the model size, simultaneously, while producing good performance for speech enhancement. Based on the promising results, we believe that the proposed framework can be deployed in various mobile and edge-computing devices.

Research Area(s)

  • Arithmetic circuit, Deep neural networks, Inference acceleration, Model compression, Speech enhancement

Citation Format(s)

IA-Net : Acceleration and Compression of Speech Enhancement using Integer-adder Deep Neural Network. / Lin, Yu-Chen; Hsu, Yi-Te; Fu, Szu-Wei; Tsao, Yu; Kuo, Tei-Wei.

Proceedings of Interspeech 2019. Interspeech, 2019. p. 1801-1805.

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review