A fresh method for understanding musical relationships through dependency trees.
― 6 min read
Electrical Engineering and Systems Science - Audio and Speech Processing
RSSThis article discusses new models that enhance speech recognition accuracy by considering longer context.
― 5 min read
LyricWhiz combines advanced models to improve lyric transcription accuracy across languages.
― 5 min read
A study on using sound recordings to identify different bird species in Africa.
― 6 min read
New method enhances learning in Spiking Neural Networks by incorporating delay adjustments.
― 6 min read
Learn how recommendation systems suggest songs based on user preferences.
― 5 min read
This article discusses challenges and techniques for managing dataset imbalance in audio classification.
― 6 min read
A new approach improves speech recognition for Romanian using lateral inhibition.
― 5 min read
Research highlights methods to protect gender privacy in spoken audio.
― 5 min read
A look into capturing emotions behind spoken words more accurately.
― 5 min read
Using pre-trained audio embeddings leads to better music classification models.
― 7 min read
Research highlights word boundaries' role in speech and EEG activity.
― 6 min read
New framework enhances speech clarity from silent videos through improved processing.
― 6 min read
Discover the blend of art and science in studying the mridangam.
― 8 min read
A new method improves custom word recognition in ASR systems for languages with limited data.
― 5 min read
Researchers develop a Conformer model to improve fake audio detection.
― 5 min read
A method to conceal gender information while ensuring identity verification in voice recognition.
― 5 min read
New methods improve early detection of Alzheimer's using speech and audio analysis.
― 7 min read
Explore sound data from 41 musical instruments with detailed recordings.
― 6 min read
Research on improving acoustic word embeddings with semantic understanding and multilingual data.
― 6 min read
New technologies improve communication for individuals with speech disorders.
― 6 min read
A new system combines transcription and translation for better communication.
― 4 min read
Whisper-AT combines speech recognition and audio tagging for improved performance.
― 5 min read
A new approach that combines speech with language models for improved translation.
― 4 min read
New method improves accuracy in turning piano audio into sheet music.
― 4 min read
This article discusses the needs and challenges in generative audio technology.
― 5 min read
New methods use cough sounds and health data to better detect tuberculosis.
― 5 min read
This study examines how voice characteristics evolve in oral cancer patients post-treatment.
― 5 min read
A new method for changing musical timbre using advanced machine learning techniques.
― 5 min read
New methods enhance speech recognition accuracy, addressing common transcription errors.
― 4 min read
A study on improving vocal sound reproduction through advanced synthesis techniques.
― 5 min read
VampNet transforms music processing through innovative token modeling techniques.
― 4 min read
Affordable wearable technology for individuals with hearing loss.
― 5 min read
A new model improves timing accuracy for lyrics in music applications.
― 6 min read
A web-based synthesizer that allows users to create music using simple gestures.
― 4 min read
A study on AI's role in generating progressive metal music.
― 6 min read
A model that creates guitar tablature reflecting famous guitarists' styles.
― 5 min read
Exploring the potential of self-supervised learning in music information retrieval.
― 6 min read
Using audio signals to identify respiratory health risks.
― 7 min read
A new method improves speech recognition speed and accuracy while reducing resource use.
― 5 min read