Article
Event Based Time-Vectors for auditory features extraction: a neuromorphic approach for low power audio recognition
Author/s | Rasetto, Marco
Domínguez Morales, Juan Pedro Jiménez Fernández, Ángel Francisco Benosman, Ryad B. |
Department | Universidad de Sevilla. Departamento de Arquitectura y Tecnología de Computadores |
Publication Date | 2021 |
Deposit Date | 2022-11-11 |
Published in |
|
Abstract | In recent years tremendous efforts have been done to advance the state of the art for Natural Language
Processing (NLP) and audio recognition. However, these efforts often translated in increased power
consumption and ... In recent years tremendous efforts have been done to advance the state of the art for Natural Language Processing (NLP) and audio recognition. However, these efforts often translated in increased power consumption and memory requirements for bigger and more complex models. These solutions falls short of the constraints of IoT devices which need low power, low memory efficient computation, and therefore they fail to meet the growing demand of efficient edge computing. Neuromorphic systems have proved to be excellent candidates for low-power low-latency computation in a multitude of applications. For this reason we present a neuromorphic architecture, capable of unsupervised auditory feature recognition. We then validate the network on a subset of Google’s Speech Commands dataset. |
Citation | Rasetto, M., Domínguez Morales, J.P., Jiménez Fernández, Á.F. y Benosman, R.B. (2021). Event Based Time-Vectors for auditory features extraction: a neuromorphic approach for low power audio recognition. ArXiv.org, arXiv:2112.07011. https://doi.org/10.48550/arXiv.2112.07011. |
Files | Size | Format | View | Description |
---|---|---|---|---|
Event Based Time-Vectors for ... | 3.451Mb | [PDF] | View/ | |