A new method enhances Automatic Speech Recognition against adversarial challenges.
― 5 min read
Computer Science - Sound
RSSLatest Articles
Latest Articles
A new method for emotional speech synthesis while preserving speaker identity.
― 6 min read
Analyzing bias in voice identification technology across different demographics.
― 5 min read
A new multi-band audio coding method improves sound quality and efficiency.
― 5 min read
Brain wave tracking shows promise in assessing language problems post-stroke.
― 8 min read
New framework improves audio recognition without extensive data access.
― 5 min read
A new model improves audio classification using advanced techniques.
― 5 min read
Researchers are finding new ways to locate sound sources accurately.
― 4 min read
A new system enhances speech signals affected by various distortions.
― 5 min read
A new method to estimate audio processing setups from sound inputs.
― 7 min read
Discover how diffusion models are changing music generation for composers.
― 5 min read
Learn how body-conduction microphones enhance speech quality despite background noise.
― 7 min read
A new system matches music to speech based on emotions without needing text.
― 5 min read
EarCough uses smart earbuds to detect user coughs accurately.
― 5 min read
A new method enhances sound recognition across diverse smart devices.
― 5 min read
A study on improving emotion detection through multiple data sources.
― 5 min read
Research teams compete in improving speech quality amidst background noise.
― 4 min read
A new model that improves speech recognition in multi-speaker settings.
― 6 min read
New methods improve speech recognition accuracy and efficiency.
― 5 min read
Recent methods improve speech recognition without relying on labeled data.
― 5 min read
LMCodec compresses audio effectively while preserving quality for clear communication.
― 5 min read
This article highlights how self-supervised learning helps improve speech recognition systems.
― 5 min read
AIOZ-GDANCE promotes research in creating group dance movements based on music.
― 5 min read
This study reveals patterns in sperm whale sounds and their potential meanings.
― 5 min read
Research improves machines' ability to locate objects that make sounds in videos.
― 8 min read
This article examines two methods for improving sound reproduction quality.
― 6 min read
Discover how music structures enhance our listening experience.
― 5 min read
Exploring new methods for segmenting music structure and their implications.
― 5 min read
A new approach to translating songs that aligns lyrics with melodies effectively.
― 7 min read
This research looks at using adaptive music in DareFightingICE for player insights.
― 6 min read
Researchers develop LIPSFUS dataset for better lip reading systems.
― 5 min read
This framework enhances speaker verification using unlabeled data and clustering techniques.
― 5 min read
A new framework enhances emotion detection using self-supervised learning.
― 6 min read
This approach links video actions and sound using physics for better sound effects.
― 7 min read
A new method boosts speech recognition using visual data with existing models.
― 7 min read
This article discusses a systematic approach to music annotation.
― 6 min read
A structured approach to music representation and performance analysis.
― 5 min read
This study improves bilingual speech models using strong language support.
― 4 min read
New model transforms sounds into clear images, bridging audio and visual information.
― 6 min read
A novel approach to generate audio captions using pre-trained language models.
― 6 min read
A new approach enhances the adaptability of speech recognition technology.
― 4 min read