Latest Articles for Audio Technology

A study on improving audio outputs from text prompts using preference optimization.

A new audio codec offering high-quality compression and rich semantic content.

A new method improves audio editing using diffusion models for precise changes.

A new system improves speech clarity in multi-speaker environments.

New methods improve clarity in isolating voices from audio mixtures.

New model improves realistic audio experiences in virtual environments.

A new dataset improves the creation of foley audio for multimedia content.

Learn about online speaker diarization and its significance in various applications.

New techniques improve guitar amplifier modeling using unpaired data and GANs.

Introducing spatial voice conversion to enhance audio realism and immersion.

A new system helps robots learn tasks using audio from real-life demonstrations.

A simple method to create voices and control emotions in speech synthesis.

A novel approach to enhance sound clarity using advanced deep learning techniques.

Innovative techniques improve loudspeaker design and sound direction.

This study focuses on improving detection of deepfake audio using advanced methods.

Research highlights the role of video in improving speech recognition in noisy environments.

Advancements in sound classification enhance audio recognition accuracy.

New dataset improves audio generation from detailed text descriptions.

A new method helps smaller models perform better using hints from larger models.

ElasticAST allows processing of variable length audio efficiently without losing important details.

A novel approach improves detection of mixed real and fake audio clips.

A new dataset combining images, text, and audio for interior scene research.

CADE improves audio detection against evolving spoofing threats using continual learning techniques.

A new dataset aims to improve speech capture using body-conduction sensors.

A team improves audio processing for speaker and language identification.

A new text-to-audio model using only public data.

A new technology simplifies equalization for audio recordings.

Improving audio quality in devices through bandwidth expansion techniques.

A new method improves voice separation in noisy settings with multiple speakers.

Wavespace offers innovative tools for better sound creation and control.

Research focuses on identifying abusive speech in audio recordings across languages.

A method to create audio that matches first-person viewpoint videos.

A study on improving methods to detect lossy audio compression for better sound quality.

Examining techniques to protect privacy while analyzing recorded conversations.

Improving binaural sound reproduction for better audio experiences in various devices.

New machine learning model enhances audio source separation techniques.

Music2Latent simplifies audio compression while maintaining high quality for various applications.

A system to enhance speech clarity in noisy environments using smart glasses.

A study on identifying hate speech moments in audio using novel techniques.

Introducing PeriodWave, a model improving audio generation speed and quality.