The paper introduces a novel production-based evaluation showing that child-directed speech (CDS) significantly improves a BabyLM's ability to generate grammatically correct language, even if standard…

This paper adapts a self-supervised learning based anonymization pipeline to the child speech domain, improving intelligibility and perceptual quality while maintaining strong privacy protection.

The paper introduces GigaSpeechBench, a comprehensive multilingual and multidimensional ASR & AST benchmark with 680 hours of human-annotated speech, featuring 12 low-resource languages, 6 Chinese dia…

The paper introduces a new quantitative metric, Contextual Alternative Choice (CAC), to rigorously test language models' syntactic and functional understanding of determiners, showing that current mod…

The paper introduces ChildEval, a large-scale benchmark designed to systematically evaluate how well large language models can infer and follow complex, child-specific preferences during long-context…

This paper investigates entrainment effects in multi-party human-agent conversations and finds limited global entrainment and cohort-dependent entrainment with the agent.

The paper introduces Dialogs, a new Russian conversational speech corpus with high-quality recordings, segmented utterances, and expressive prosody labels.

KidsNanny is a two-stage multimodal content moderation pipeline that achieves high accuracy and efficiency in detecting child safety threats, particularly excelling in text-embedded content.

This paper explores the effect of conversational timing properties on automatic speech recognition (ASR) systems by controlling and optimizing pause and overlap timing distributions.

The paper introduces BabyCL, a continual multimodal learning framework that processes egocentric video data in a single chronological pass, demonstrating that meaningful word-referent mappings can be…

The paper introduces the Designed Vocalizations Dataset for AI-based voice conversion research on non-human vocalizations and effects, providing a standardized test set and benchmark results.

A lightweight framework for automated pronunciation assessment using native speech resources and unsupervised or lightly calibrated methods.

PolySpeech-100 introduces a massive, multi-lingual benchmark covering 110 linguistic variants to rigorously test Speech-LLMs, demonstrating that open-source models struggle with low-resource languages…

The paper proposes RTFree-F5, a method to make flow-matching TTS models like F5-TTS independent of reference transcripts, improving performance and naturalness for dysarthric speakers.

The paper introduces SPEARBench, a benchmark for evaluating naturalness in speech-to-speech language models using a multidimensional protocol.

This paper investigates neural activity during five auditory conditions using EEG recordings from a 5-year-old participant, revealing condition-specific modulation of neural oscillatory activity and d…

BuddyBench introduces a novel, privacy-constrained multi-task benchmark that integrates longitudinal learning trajectories, standardized clinical assessments, and randomized trial data to advance pedi…

This paper investigates the correlation between dimensions of self-supervised speech features and speech characteristics, finding that content dimensions primarily capture intensity, formants, and voi…