Latest Articles for Audio Technology

Advanced techniques for ensuring audio authenticity in the age of voice cloning.

A new method trains audio captioning systems using only text descriptions.

M-AUDIODEC compresses multi-channel audio while retaining speaker position and quality.

A novel system enhances spatial audio compression for clearer sound and efficiency.

Research reveals new models to enhance voice clarity in smart earbuds.

New methods improve tiny models for better speech enhancement using less resources.

RECAP uses advanced techniques to generate accurate audio captions without retraining.

A new approach enhances speaker diarization by integrating semantic data into the process.

Improving the way we identify sound sources using audio-visual data.

A new approach assesses audio quality using multiple microphones in various environments.

A new method enhances sound separation across different frequencies.

Explore advancements in echo cancellation to enhance call quality.

Investigating deepfake audio to enhance transcription models for less common languages.

A novel method to watermark audio created by diffusion models for ownership protection.

Study compares sound localization accuracy of four-channel and two-channel audio formats.

A new audio processing method enhances speaker anonymity while maintaining speech clarity.

Introducing new models for better speech extraction in noisy environments.

Synthia's Melody aids researchers in audio model testing against varied data.

Research focuses on improving ASR systems for unsegmented audio.

Research focuses on optimizing synthesizers for human vocalizations in various media.

Research introduces an effective method for improving speech clarity in noisy settings.

Learn how ultraspherical polynomials improve audio technology and sound directionality.

Using AI to improve how we recreate sound in different environments.

Learn about real-valued beamforming and its benefits for microphone arrays.

Discover how MIMO systems improve sound analysis in various environments.

New techniques improve sound direction estimation for various audio settings.

Research reveals methods to adjust sound behavior in rooms for improved clarity.

A study on sound synthesis and its evaluation in controlled environments.

PAM offers a novel way to measure audio quality without needing reference recordings.

A new model enhances machines' understanding of spatial audio.

A new tool helps users modify sounds easily through simple text instructions.

A new system to evaluate audio codec performance across various applications.

Research highlights new models for better audio quality in various environments.

CLAPSep enhances sound separation using pre-trained models and user queries for improved accuracy.

Exploring how sound field reconstruction impacts audio experiences across various applications.

New tools enhance voice recording editing and production quality.

Discover how generative equalization breathes new life into old music recordings.

A new method improves sound processing through automatic tuning of Feedback Delay Networks.

This study investigates the effectiveness of multilingual models in detecting audio deepfakes.

Exploring advanced methods for sound projection in compression drivers.