Research introduces MOSA dataset, enhancing understanding of music's visual and auditory aspects.
― 7 min read
Electrical Engineering and Systems Science - Audio and Speech Processing
RSSmHuBERT-147 processes speech in multiple languages efficiently.
― 4 min read
A new approach to audio captioning reduces reliance on paired data.
― 5 min read
New methods improve how machines recognize emotions in human speech.
― 5 min read
A look at new methods in understanding overlapping speech during conversations.
― 8 min read
Investigating vulnerabilities in audio watermarking methods against real-world threats.
― 7 min read
PianoMotion10M provides detailed hand movements to aid piano learners.
― 6 min read
A new model improves sound matching with visual actions in videos.
― 11 min read
New model improves realistic audio experiences in virtual environments.
― 7 min read
This study examines audio methods for tracking pedestrian movement in urban areas.
― 7 min read
A new dataset improves the creation of foley audio for multimedia content.
― 6 min read
New methods enhance speech recognition in noisy environments using adaptive techniques.
― 6 min read
SPEAR predicts sound behavior in 3D spaces using minimal data collection.
― 6 min read
A new method improves translating mixed-language speech into English.
― 5 min read
A new method enhances speaker verification accuracy in challenging radio environments.
― 6 min read
New method targets rhythm changes for stealthy speech attacks.
― 5 min read
GAMA improves audio processing by merging sound and language insights.
― 5 min read
A new system helps separate speech from noise for clearer communication.
― 6 min read
GigaSpeech 2 offers a vast dataset for low-resource languages to improve speech recognition.
― 5 min read
A new model enhances text-to-speech technology with efficiency and adaptability.
― 6 min read
A novel method optimizing speech analysis and synthesis using vocal tract movements.
― 7 min read
This study examines how gestures affect learning from virtual agents.
― 6 min read
DExter uses AI to create expressive piano music from written scores.
― 5 min read
Learn about online speaker diarization and its significance in various applications.
― 6 min read
New benchmark tool assesses discrete audio tokens for various speech processing tasks.
― 8 min read
A new method for music generation using self-similarity matrices and attention systems.
― 7 min read
New techniques improve guitar amplifier modeling using unpaired data and GANs.
― 7 min read
A new method improves voice conversion between languages while preserving speaker traits.
― 4 min read
A new method for understanding how audio models make predictions.
― 5 min read
Introducing spatial voice conversion to enhance audio realism and immersion.
― 6 min read
WavRx analyzes speech for health while protecting privacy, showing promising diagnostic results.
― 7 min read
Research explores how speech analysis can predict suicide risk, considering gender differences.
― 5 min read
This paper presents a system to create visuals that respond to music.
― 7 min read
A new system helps robots learn tasks using audio from real-life demonstrations.
― 7 min read
New methods improve accuracy in recognizing overlapping sounds across diverse audio sources.
― 6 min read
A new method combines acoustic features and confidence scores for better error correction.
― 5 min read
SecureSpectra offers a new way to safeguard audio identity against deepfake threats.
― 5 min read
Combining physics and geometry for improved acoustic scattering predictions.
― 5 min read
A new system for accurate and fast speech translation across multiple languages.
― 6 min read
A simple method to create voices and control emotions in speech synthesis.
― 5 min read