Caption Studio is a transparency-first speech and audio intelligence platform that provides automated transcription, speaker diarization, speech analytics, signal-level audio analysis, and subtitle ge…

The paper introduces AudioHijack, a framework that successfully demonstrates context-agnostic and imperceptible auditory prompt injection attacks, showing that commercial Large Audio-Language Models c…

The paper introduces the Real World Voice EQ Bench, a multidimensional benchmark for evaluating voice AI across text-to-speech, speech-to-speech, speech understanding, and automatic speech recognition…

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.

This paper proposes a novel layer-wise decision fusion method for fake audio detection using deep speech models, achieving the best cross-dataset performance.

The study tests the semantic independence of Resemble AI's deepfake audio detector, DETECT-3B-Omni, using 10,240 audio samples from various speakers and AI voice-cloning systems, and shows that the ac…

The paper introduces HAIM, a new benchmark dataset designed to move AI music detection beyond simple binary classification by tracking specific stages and types of AI integration in music production.

This paper presents ADAC, a compiler that converts trained differentiable audio models into efficient FAUST code for real-time audio effects.

The authors identify confusion patterns in a large audio-language model and use them to curate diagnostic data for fine-tuning, achieving higher accuracy than the baseline.

UniAudio-Token is a framework that enhances existing semantic speech tokenizers with general audio perception, allowing them to handle diverse audio types while maintaining high-fidelity speech capabi…

This paper conducts subjective assessments to evaluate the preference and spatial audio attributes of headrest-integrated speakers for immersive audio scenarios in automobiles.

This paper characterizes the gap between current DNN-based speech enhancement systems and hearing aid constraints, and proposes a lightweight architecture to meet these constraints.

The paper introduces Acoustic Interference Attack (AIA), a novel jailbreak method that bypasses Large Audio Language Model (LALM) safety alignments by manipulating the underlying acoustic latent seman…

This paper proposes a data-driven method for automatic blind audio equalization using a deep neural network and semantic embeddings.