Projects per year
Abstract
This paper introduces neural architecture search (NAS) for the automatic discovery of end-to-end keyword spotting (KWS) models for limited resource environments. We employ a differentiable NAS approach to optimize the structure of convolutional neural networks (CNNs) operating on raw audio waveforms. After a suitable KWS model is found with NAS, we conduct quantization of weights and activations to reduce the memory footprint. We conduct extensive experiments on the Google speech commands dataset. In particular, we compare our end-to-end models to mel-frequency cepstral coefficient (MFCC) based CNNs. For quantization, we compare fixed bit-width quantization and trained bit-width quantization. Using NAS only, we were able to obtain a highly efficient model with an accuracy of 95.55% using 75.7k parameters and 13.6M operations. Using trained bit-width quantization, the same model achieves a test accuracy of 93.76% while using on average only 2.91 bits per activation and 2.51 bits per weight
Original language | English |
---|---|
Title of host publication | 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings |
Publisher | Institute of Electrical and Electronics Engineers |
Pages | 3423-3427 |
Number of pages | 5 |
ISBN (Electronic) | 9781665405409 |
DOIs | |
Publication status | Published - 2022 |
Event | 47th IEEE International Conference on Acoustics, Speech and Signal Processing: ICASSP 2022 - Virtual, Online, Singapore Duration: 22 May 2022 → 27 May 2022 |
Publication series
Name | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings |
---|---|
Volume | 2022-May |
ISSN (Print) | 1520-6149 |
Conference
Conference | 47th IEEE International Conference on Acoustics, Speech and Signal Processing |
---|---|
Abbreviated title | ICASSP 2022 |
Country/Territory | Singapore |
City | Virtual, Online |
Period | 22/05/22 → 27/05/22 |
Keywords
- keyword spotting
- neural architecture search
- quantization
ASJC Scopus subject areas
- Software
- Signal Processing
- Electrical and Electronic Engineering
Fields of Expertise
- Information, Communication & Computing
Projects
- 1 Active