# SpeechYOLO: Detection and Localization of Speech Objects

## TL;DR

SpeechYOLO adapts object detection techniques from vision to audio, enabling effective localization and classification of speech segments within audio signals, demonstrating promising results on keyword spotting tasks.

## Contribution

This work introduces SpeechYOLO, a novel approach applying YOLO-inspired object detection to speech, combining localization and classification in a single neural network.

## Key findings

- Outperforms existing algorithms in keyword spotting tasks
- Effective localization of speech segments within audio signals
- Compatible with both read and spontaneous speech datasets

## Abstract

In this paper, we propose to apply object detection methods from the vision domain on the speech recognition domain, by treating audio fragments as objects. More specifically, we present SpeechYOLO, which is inspired by the YOLO algorithm for object detection in images. The goal of SpeechYOLO is to localize boundaries of utterances within the input signal, and to correctly classify them. Our system is composed of a convolutional neural network, with a simple least-mean-squares loss function. We evaluated the system on several keyword spotting tasks, that include corpora of read speech and spontaneous speech. Our system compares favorably with other algorithms trained for both localization and classification.