New machine learning models improve speech clarity for hearing aid users.
― 6 min read
Electrical Engineering and Systems Science - Audio and Speech Processing
RSSResearch explores low-frequency audio to protect privacy in social behavior studies.
― 5 min read
Exploring how sound behaves in multi-room environments and its implications in technology.
― 6 min read
New AI tools are simplifying music editing with innovative techniques and improved precision.
― 5 min read
Preset-Voice Matching improves speech translation while ensuring privacy and reducing risks.
― 6 min read
A new system helps musicians create music with greater control and precision.
― 7 min read
A new tool to assess replication in AI-made music.
― 7 min read
A new text-to-audio model using only public data.
― 5 min read
A new dataset aims to improve understanding of code-switching across multiple languages.
― 5 min read
This article examines gender balance in French news broadcasts across different topics.
― 5 min read
Rasa dataset advances text-to-speech for Indian languages with neutral and expressive speech.
― 6 min read
New methods improve machine understanding of human emotions in speech.
― 4 min read
Simplifying AI tools can empower artists to enhance their creative expression.
― 5 min read
MusiConGen enhances user control in text-to-music generation.
― 6 min read
Researchers improve speech decoding using EEG to help those with speech impairments.
― 7 min read
A new model improves speech clarity by targeting noise and echoes.
― 6 min read
J-CHAT provides a large, open-source dataset for enhancing spoken dialogue systems.
― 5 min read
New methods enable musicians to create instruments from sound prompts.
― 5 min read
Examining how codecs retain emotional tones in voice data.
― 5 min read
Learn how IP broadcasting and audio tagging reshape content delivery.
― 5 min read
A look at how technology and musicians collaborate in a unique performance.
― 7 min read
A robot plays music in a store to improve customer enjoyment.
― 7 min read
A new technology simplifies equalization for audio recordings.
― 5 min read
This article discusses methods to enhance ASR for languages with limited data.
― 6 min read
A new method simplifies synthesizer sound matching for musicians.
― 5 min read
A new method enhances clarity in electric guitar recordings by tackling distortion effects.
― 6 min read
A new tool enhances how users edit music tracks efficiently.
― 5 min read
Studying marmoset vocalizations using advanced classification methods and audio analysis.
― 6 min read
A study on enhancing transcription accuracy through improved prompt design.
― 5 min read
A framework for improving AI sentiment analysis in healthcare conversations.
― 6 min read
New methods improve realism in animations for media and virtual assistants.
― 5 min read
Combining wake words and speaker recognition enhances safety in voice technology.
― 5 min read
A new approach enhances SER systems by using noise environment descriptions.
― 6 min read
A new model aims to improve speech translation quality through integrated systems.
― 5 min read
Explore the growing importance of speech editing for content creators.
― 5 min read
New techniques enhance synthetic voice generation with minimal data.
― 5 min read
A novel tool analyzes sperm whale codas for insights into their social interactions.
― 6 min read
New methods help study and protect endangered manatees through underwater sound monitoring.
― 5 min read
A new framework improves connection between faces and voices, especially in noisy settings.
― 5 min read
A study improves heart rate estimation and murmur detection using recordings.
― 5 min read