Pith. sign in

REVIEW

Keyword Spotting System and Evaluation of Pruning and Quantization Methods on Low-power Edge Microcontrollers

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2208.02765 v1 pith:YACORVST submitted 2022-08-04 cs.SD cs.AIcs.AReess.AS

Keyword Spotting System and Evaluation of Pruning and Quantization Methods on Low-power Edge Microcontrollers

classification cs.SD cs.AIcs.AReess.AS
keywords devicesedgepruningmicrocontrollersquantizationsystemdifferentincluding
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Keyword spotting (KWS) is beneficial for voice-based user interactions with low-power devices at the edge. The edge devices are usually always-on, so edge computing brings bandwidth savings and privacy protection. The devices typically have limited memory spaces, computational performances, power and costs, for example, Cortex-M based microcontrollers. The challenge is to meet the high computation and low-latency requirements of deep learning on these devices. This paper firstly shows our small-footprint KWS system running on STM32F7 microcontroller with Cortex-M7 core @216MHz and 512KB static RAM. Our selected convolutional neural network (CNN) architecture has simplified number of operations for KWS to meet the constraint of edge devices. Our baseline system generates classification results for each 37ms including real-time audio feature extraction part. This paper further evaluates the actual performance for different pruning and quantization methods on microcontroller, including different granularity of sparsity, skipping zero weights, weight-prioritized loop order, and SIMD instruction. The result shows that for microcontrollers, there are considerable challenges for accelerate unstructured pruned models, and the structured pruning is more friendly than unstructured pruning. The result also verified that the performance improvement for quantization and SIMD instruction.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.