2025/12/10 by Grundhuber, Philipp, Halimeh, Mhd Modar, Strauß, Martin +1
Computer Science · Medicine · #Speech and Audio Processing #Speech Recognition and Synthesis #Voice and Speech Disorders
paper · doi:10.48550/arxiv.2512.09713
Speech Activity Detection (SAD) systems often misclassify singing as speech, leading to degraded performance in applications such as dialogue enhancement and automatic speech recognition. We introduce Singing-Robust Speech Activity Detection ( SR-SAD ), a neural network designed to robustly detect speech in the presence of singing. Our key contributions are: i) a training strategy using controlled ratios of speech and singing samples to improve discrimination, ii) a computationally efficient model that maintains robust performance while reducing inference runtime, and iii) a new evaluation metric tailored to assess SAD robustness in mixed speech-singing scenarios. Experiments on a challenging dataset spanning multiple musical genres show that SR-SAD maintains high speech detection accuracy (AUC = 0.919) while rejecting singing. By explicitly learning to distinguish between speech and singing, SR-SAD enables more reliable SAD in mixed speech-singing scenarios.