This study explores bias in audio models used for instrument recognition.
― 6 min read
Electrical Engineering and Systems Science - Audio and Speech Processing
RSSThis study explores a deep learning approach to accurately classify music genres.
― 7 min read
Research explores methods for identifying topics directly from audio recordings.
― 5 min read
New method improves sound source location tracking in shallow aquatic environments.
― 7 min read
A new model connects phonetics and acoustics for better speech technology.
― 7 min read
This study highlights the role of self-supervised learning in detecting emotions from audio data.
― 6 min read
A new interface simplifies music creation for beginners using text-to-audio technology.
― 5 min read
Research highlights the improvements AI can bring to hearing aids in noisy settings.
― 5 min read
New method refines mislabeled data, enhancing music source separation.
― 6 min read
Advancements in decoding how people focus on sounds using brain activity.
― 5 min read
A new method improves sound clarity and localization using a hybrid approach.
― 5 min read
CMNet improves voice clarity by reducing echo in communication devices.
― 5 min read
A new method enhances the classification of underwater sounds from vessels using neural networks.
― 5 min read
Research aims to improve clarity in hearing aids for better communication.
― 5 min read
A new method to improve speech quality using energy-efficient networks.
― 5 min read
Research highlights cow communication to improve dairy farming practices.
― 5 min read
MuReNN combines parametric and nonparametric models for improved audio analysis.
― 5 min read
Revolutionizing animal communication research with innovative audio and language integration.
― 4 min read
Research shows benefits of multiple microphones for detecting and locating speakers.
― 5 min read
Introducing a new model for clearer speech in noisy environments.
― 5 min read
A new method improves audio matching using images, enhancing realism in audio environments.
― 7 min read
A dataset connects emotions to MIDI songs using song lyrics analysis.
― 7 min read
Improving speech quality through innovative methods and multilingual datasets.
― 6 min read
New techniques aim to improve audio quality by addressing packet loss.
― 5 min read
New systems are designed to detect fake audio recordings with improved accuracy.
― 5 min read
New systems improve speaker identification using both audio and visual data.
― 5 min read
MoisesDB offers a detailed dataset for advanced music sound separation.
― 6 min read
Using LLMs to create a vast dataset for music captioning.
― 6 min read
Researchers are improving pronunciation training with new technologies for language learners.
― 5 min read
HierVST transforms voices seamlessly, enhancing audio quality without needing extensive data.
― 5 min read
A unified approach enhances music analysis by integrating multiple structural elements.
― 5 min read
Research focuses on classifying child-adult speech using unlabelled data.
― 5 min read
Research develops a model to accurately measure engagement in conversations.
― 6 min read
DAVIS offers a fresh way to tackle audio and visual sound separation.
― 5 min read
A new method enhances accurate identification of sound-producing objects in videos.
― 6 min read
DiffProsody enhances speech synthesis speed and quality through innovative prosody generation.
― 4 min read
Deep learning models improve sound field reconstruction in complex environments.
― 7 min read
New technology aims to restore music quality lost in loudness compression.
― 5 min read
New method promises quicker identification of speech disorders like aphasia.
― 5 min read
New method uses ultrasonic sounds to confuse speech recognition systems without detection.
― 6 min read