Event Based Time-Vectors for auditory features extraction: a neuromorphic approach for low power audio recognition
This addresses the need for efficient edge computing in IoT devices, offering a low-power solution for audio recognition.
The paper tackles the problem of high power consumption and memory requirements in audio recognition by proposing a neuromorphic architecture for low-power, unsupervised auditory feature extraction, validated on a subset of Google's Speech Commands dataset.
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.