Search papers, labs, and topics across Lattice.
The authors introduce ChildVox, a benchmark designed to evaluate audio and speech models on a diverse range of child-related acoustic signals, spanning from physiological sounds to spoken language across developmental stages. It integrates over 20 sub-tasks across 17 datasets, facilitating cross-corpus and cross-domain comparisons. Evaluations of various audio and speech foundation models reveal ChildVox's utility in identifying high-performing models for recognizing children's acoustic signals and supporting applications like language level assessment and speech production tracking.
ChildVox reveals the current capabilities and limitations of audio and speech models in understanding the nuanced and developing acoustic world of children.
We present ChildVox, a novel benchmark for characterizing the diverse acoustic signals through which children communicate. Specifically, ChildVox follows the full developmental trajectory from birth through school age, covering physiological sounds, non-linguistic vocalizations, canonical syllables, and spoken language. ChildVox integrates more than 20 sub-tasks across 17 child-centered audio and speech datasets, enabling systematic cross-corpus and cross-domain comparison. We evaluate a representative range of audio and speech foundation models, including self-supervised, ASR-oriented, and large audio-language models, on tasks including physiological sound classification, vocalization and canonical syllables modeling, and speech quality assessment and recognition. Benchmark results show that ChildVox provides a suite of high-performance models in recognizing a wide range of acoustic signals from children, supporting downstream applications such as characterizing children's language levels and tracking speech production with age.
