A new system connects emotional images to music for improved discovery.
― 6 min read
Electrical Engineering and Systems Science - Audio and Speech Processing
RSSA new system enhances audio recordings for better listening experiences.
― 6 min read
A novel approach reduces data labeling while enhancing audio classification accuracy.
― 5 min read
A new system improves speech quality and expressiveness for paragraph synthesis.
― 5 min read
Discover methods for assessing AI-created music quality through subjective and objective evaluation.
― 5 min read
Research focuses on tongue movements to aid speech therapy and language learning.
― 4 min read
This study examines how gender affects voice biometrics' utility, privacy, and fairness.
― 6 min read
New pruning methods enhance zero-shot multi-speaker text-to-speech model performance.
― 7 min read
Research on emotion recognition in emergency call interactions reveals significant insights.
― 4 min read
New methods for selecting speech data minimize labeling while improving recognition accuracy.
― 5 min read
A new method enhances emotion recognition in speech by analyzing time and frequency.
― 5 min read
Explore how quantum tools transform music production for artists.
― 5 min read
A new method enhances speech quality ranking using listener preference scores.
― 5 min read
A method to enhance ASR systems for users who stutter.
― 5 min read
Challenges in accessing audio data hinder research opportunities.
― 5 min read
New methods improve clarity in noisy environments through advanced sound processing.
― 5 min read
A newly developed system generates realistic French speech for a competition.
― 5 min read
New methods improve efficiency and accuracy in voice recognition systems.
― 5 min read
New methods improve speech processing and generation in language models.
― 5 min read
New techniques improve audio clarity in noisy environments.
― 6 min read
New methods improve keyword spotting using available reading speech data.
― 4 min read
A look into region-customizable sound extraction methods for clearer audio.
― 5 min read
New single-step methods improve accuracy in formant tracking for speech sounds.
― 4 min read
A fresh look at advancements in spoken language science methods and applications.
― 6 min read
This study examines the difficulties of using contrastive learning for music video understanding.
― 6 min read
A new approach enhances the integration of speech with language models.
― 7 min read
Using self-supervised learning to enhance predictions of speech movements in dysarthria.
― 5 min read
A new metric to assess the alignment of dance styles with music.
― 7 min read
Examining how pretrained language models improve text-to-speech quality.
― 5 min read
A new model evaluates audio perception through human feedback using Best-Worst Scaling.
― 5 min read
New methods improve the clarity of audio components in music tracks.
― 6 min read
BandIt enhances audio source separation using innovative deep learning techniques.
― 5 min read
Tailoring emotion recognition technology improves accuracy for diverse speakers.
― 6 min read
Study reveals serious threats in voice recognition using morph samples.
― 5 min read
A detailed dataset combining Mozart's sonatas with piano performances and expert annotations.
― 5 min read
A new earbud design improves sound clarity using bone conduction technology.
― 7 min read
A new lightweight model improves pitch estimation using self-supervised learning techniques.
― 7 min read
A new approach to improve music segment identification and analysis.
― 5 min read
New methods developed to identify fake songs amidst growing concerns.
― 5 min read
Cleancoder enhances ASR systems by reducing background noise for clearer speech understanding.
― 4 min read