paper-with-me

Papers

How Tiny Can Analog Filterbank Features Be Made for Ultra-low-power On-device Keyword Spotting?

2023-04-17 · Subhajit Ray, Xinghua Sun, Nolan Tremelling, Maria Gordiyenko, Peter Kinget

Analog feature extraction is a power-efficient and re-emerging signal processing paradigm for implementing the front-end feature extractor in on device keyword-spotting systems. Despite its power efficiency and re-emergence, there is little consensus on what values the architectural parameters of its critical block, the analog filterbank, should be set to, even though they strongly influence power consumption. Towards building consensus and approaching fundamental power consumption limits, we find via simulation that through careful selection of its architectural parameters, the power of a typical state-of-the-art analog filterbank could be reduced by 33.6x, while sacrificing only 1.8% in downstream 10-word keyword spotting accuracy through a back-end neural network.

📄 PDF Abstract BibTeX arXiv:2304.08541

Code (0)

등록된 구현이 없습니다.

Tasks

Keyword Spotting

Similar Papers 제목 키워드 기반

VAD to the Bone: Ultra-Tiny Speech Activity Detection for Edge Deployment

2026-07-28 · Stephen Bauer, Sheila Seidel, Shanza Iftikhar, Scott Veidenheimer 외 arxiv

Voice activity detection (VAD) triggers downstream speech processing in always-on systems under strict memory, latency, and compute constraints. Recent compact models report strong accuracy but rely on components that ar…

Activity Detection

Filterbank design for end-to-end speech separation

2019-10-23 · Manuel Pariente, Samuele Cornell, Antoine Deleforge, Emmanuel Vincent

Single-channel speech separation has recently made great progress thanks to learned filterbanks as used in ConvTasNet. In parallel, parameterized filterbanks have been proposed for speaker recognition where only center f…

Speaker RecognitionSpeech Separation

A Universal Learnable Audio Frontend

2021-01-01 · ICLR 2021 1 · Neil Zeghidour, Olivier Teboul, Félix de Chaumont Quitry, Marco Tagliasacchi

Mel-filterbanks are fixed, engineered audio features which emulate human perception and have lived through the history of audio understanding up to today. However, their undeniable qualities are counterbalanced by the fu…

Audio Classification

LEAF: A Learnable Frontend for Audio Classification

2021-01-21 · Neil Zeghidour, Olivier Teboul, Félix de Chaumont Quitry, Marco Tagliasacchi

Mel-filterbanks are fixed, engineered audio features which emulate human perception and have been used through the history of audio understanding up to today. However, their undeniable qualities are counterbalanced by th…

Audio ClassificationClassificationGeneral Classification

Flexible and Fully Quantized Ultra-Lightweight TinyissimoYOLO for Ultra-Low-Power Edge Systems

2023-07-12 · Julian Moosmann, Hanna Mueller, Nicky Zimmerman, Georg Rutishauser 외

This paper deploys and explores variants of TinyissimoYOLO, a highly flexible and fully quantized ultra-lightweight object detection network designed for edge systems with a power envelope of a few milliwatts. With exper…

object-detectionObject Detection