Real-time low-resource phoneme recognition on edge devices

TL;DR

This paper introduces a method for creating highly accurate, low-resource speech recognition models suitable for real-time use on edge devices, enabling support for any language with minimal data and storage requirements.

Contribution

The paper presents a novel approach to train language-agnostic speech recognition models that are efficient and deployable on resource-constrained edge devices.

Findings

Models achieve high accuracy with minimal training data

Significantly reduced storage and memory requirements

Enables real-time recognition on mobile and embedded devices

Abstract

While speech recognition has seen a surge in interest and research over the last decade, most machine learning models for speech recognition either require large training datasets or lots of storage and memory. Combined with the prominence of English as the number one language in which audio data is available, this means most other languages currently lack good speech recognition models. The method presented in this paper shows how to create and train models for speech recognition in any language which are not only highly accurate, but also require very little storage, memory and training data when compared with traditional models. This allows training models to recognize any language and deploying them on edge devices such as mobile phones or car displays for fast real-time speech recognition.