The study demonstrates that self‑supervised speech embeddings can track how children’s speech converges toward adult patterns over development. Using HuBERT‑BASE embeddings extracted from over 925 hours of child‑caregiver recordings, the researchers found that the acoustic distance between a child’s vocalizations and those of their female caregiver decreased with the child’s hearing age, even after controlling for pitch and vocalization length. This single distance metric also correlated with several standardized speech and language assessments from infancy through preschoolhood, suggesting a scalable, language‑neutral way to monitor spoken language development in everyday settings.
arXiv:2509. 15001v3 Announce Type: replace-cross Abstract: Child-centered daylong recordings are essential for studying early language development, but existing speech models trained on clean adult data perform poorly due to acoustic and linguistic differences.
The paper presents a method to automatically identify utterances in child-centered daylong audio recordings that can be reliably transcribed by modern ASR systems, enabling accurate transcription of a substantial portion of the speech. On four English corpora, the approach achieves a median WER of 0% and a mean WER of 16% when transcribing 30% of the total speech, compared to a median WER of 52% when transcribing all speech. Word frequency distributions from the automatic transcripts correlate strongly with manual annotations (r = 0.94 overall, r = 0.99 for frequent words).
arXiv:2606. 01134v1 Announce Type: cross Abstract: Automatically distinguishing child-directed speech from adult-directed speech in long-form recordings is key to scalable analyses of children's language environments.
arXiv:2606. 10213v1 Announce Type: cross Abstract: Speech sound disorders affect approximately 44% of Korean pediatric communication disorder cases, yet automated assessment tools for Korean toddler speech remain underdeveloped.
arXiv:2608. 11587v1 Announce Type: cross Abstract: Recent advances in model design and self-supervised audio representations have improved speech and audio understanding, yet infant-centered naturalistic recordings remain challenging due to limited labeled data, low signal-to-noise ratio, and cross-family domain shifts.
Recent advances in model design and self-supervised audio representations have improved speech and audio understanding, yet infant-centered naturalistic recordings remain challenging due to limited labeled data, low signal-to-noise ratio, and cross-family domain shifts. We present a family-conditioned, multi-tier audio tagger that combines a LoRA-finetuned Whisper encoder with a lightweight, target-speaker-aware Transformer for long-context inference and framewise prediction across tiers.
arXiv:2606. 16505v1 Announce Type: cross Abstract: Understanding speaker confidence is crucial in educational settings, as it can enhance personalised feedback and improve learning outcomes.
arXiv:2607. 03201v1 Announce Type: cross Abstract: Long-form recordings (LFRs) of child-centered audio are ecologically valid sources for studying early language development, but three problems limit their use.
arXiv:2609.35952v1 Announce Type: cross Abstract: We introduce HEAR (Human-recorded Evaluation of Audio-LLM bias by Real speakers), a large-scale, ecologically valid benchmark comprising 87k real hum...
arXiv:2609.14743v1 Announce Type: new Abstract: Pure speech language models often lag behind text and speech-text language models in generating coherent content, but this gap is difficult to quantify...
Automatic speech recognition (ASR) systems exhibit unequal error rates across speaker groups, motivating interventions on their internal representations. We ask whether speaker-linked attributes that...
arXiv:2505. 23378v3 Announce Type: replace Abstract: Speaker-dependent modelling can substantially improve performance in speech-based health monitoring applications.