Speechyolo: Detection And Localization Of Speech Objects

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.

Stats

• citations17
• S2 citations—
• github stars0
• HF likes0
• heat score9.41
• arxiv keysegal2019speechyolo

Related papers

• I See What You Hear: A Vision-inspired Method To Localize Words (2022)0.00
• SAMO: Speaker Attractor Multi-center One-class Learning For Voice Anti-spoofing (2022)10.74
• Jointly Discovering Visual Objects And Spoken Words From Raw Sensory Input (2018)14.27
• SLOGD: Speaker Location Guided Deflation Approach To Speech Separation (2019)0.00
• Speech Recognition: Keyword Spotting Through Image Recognition (2018)0.00
• Object Referring In Visual Scene With Spoken Language (2017)7.16
• Fine-grained Grounding For Multimodal Speech Recognition (2020)5.84
• Learning To Detect Dysarthria From Raw Speech (2018)11.85