.png){kind=icon}
返回
Error-Diffusion Based Speech Feature Quantization for Small-Footprint Keyword Spotting
.png){kind=icon}
OA
AI
DOI：10.1109/LSP.2022.3179208.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Neural network based keyword spotting (KWS) system is a critical component for user interaction in current smart devices. Although small-footprint networks have been widely explored to reduce deployment overhead, low-precision input feature representation still lacks in-depth research. In this letter, an error-diffusion based speech feature quantization method is proposed. Specifically, our algorithm adapts image processing to quantize the input speech feature maps in arbitrary bits. Experiments show that in the 10-keyword KWS task, our 3-bit representation only brings a 0.45% average accuracy drop compared to the full-precision log-Mel spectrograms while others drop over 3%. In the 2 keywords task, our 3-bit representation produces no significant differences, while 1-bit quantization only leads to an average of 1.7% accuracy drop and is even capable of handling similar keywords and imbalanced data distribution. The result proves our method, to the best of our knowledge, is the first practical method that supports as low as 1-bit quantization for single-channel speech features in small-footprint KWS. In addition, we analyze the impact of error-diffusion directions and conclude that time-direction diffusion is more suitable for temporal convolutional networks.
Keyword:
Quantization (signal)
Task analysis
Spectrogram
Signal processing algorithms
Filter banks
Standards
Speech processing
Keyword spotting
speech feature quantization
error diffusion
image processing
convolutional neural networks
期刊
IF:
9.6
论文数:
1.1W
被引数:
1.7W
机构
引用论文
Efficacy of Strattera in Children and Adolescents with Attention Deficit Hyperactivity Disorder
PREAI
分享收藏分享收藏Use of SIMD Vector Operations to Accelerate Application Code Performance on Low-Powered ARM and Intel Platforms.png)
2013 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum
OAAI
2013 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd ForumIF0
OAAI分享收藏Polaritons dispersion in a composite ferrite-semiconductor structure near gyrotropic-nihility stateOAAI
OAAI分享收藏
查看更多内容