The paper proposes methods for generating global prosodic embeddings using auto-encoder models of pitch and energy, demonstrating competitive or superior performance under challenging conditions.

A Wave-U-Net model is trained to extract a fundamental waveform from input speech signals for accurate and robust instantaneous pitch estimation.

This study demonstrates that the tone of a prompt significantly affects the accuracy of various LLMs, requiring users to exercise caution regarding tone-robust reliability.

The paper proposes a Lagrangian sub-flow (LSF) framework and geometric diagnostic signals to improve out-of-distribution detection using Continuous Normalizing Flows, overcoming the likelihood paradox…

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…

MOSS-Audio is a unified audio-language model designed for comprehensive understanding of speech, environmental sounds, and music, achieving strong performance across various audio-grounded tasks.

The paper introduces ToxiAlert-Bench, a large-scale audio dataset that uniquely annotates both textual and paralinguistic sources of toxicity, and proposes a dual-head neural network that significantl…