CryCeleb: A Speaker Verification Dataset Based on Infant Cry Sounds

2023/05/01 by Budaghyan, David, Onu, Charles C., Gorin, Arsenii +2 · 3 citations
#Artificial Intelligence (cs.AI) #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2305.00969

Abstract

This paper describes the Ubenwa CryCeleb dataset - a labeled collection of infant cries - and the accompanying CryCeleb 2023 task, which is a public speaker verification challenge based on cry sounds. We released more than 6 hours of manually segmented cry sounds from 786 newborns for academic use, aiming to encourage research in infant cry analysis. The inaugural public competition attracted 59 participants, 11 of whom improved the baseline performance. The top-performing system achieved a significant improvement scoring 25.8% equal error rate, which is still far from the performance of state-of-the-art adult speaker verification systems. Therefore, we believe there is room for further research on this dataset, potentially extending beyond the verification task.

Cited by

• Automated Analysis of Naturalistic Recordings in Early Childhood: Applications, Challenges, and Opportunities
• Speech transformer models for extracting information from baby cries
• Infant Cry Detection In Noisy Environment Using Blueprint Separable Convolutions and Time-Frequency Recurrent Neural Network

Related

• Infant Crying Detection in Real-World Environments
• Towards the Synthesis of Non-speech Vocalizations
• ICSD: An Open-source Dataset for Infant Cry and Snoring Detection
• Infant Cry Detection Using Causal Temporal Representation
• Proceedings of the ICML 2022 Expressive Vocalizations Workshop and Competition: Recognizing, Generating, and Personalizing Vocal Bursts