Cleancoder enhances ASR systems by reducing background noise for clearer speech understanding.
― 4 min read
Electrical Engineering and Systems Science - Audio and Speech Processing
RSSRADIO creates realistic talking faces using just one reference image.
― 6 min read
RoDia provides crucial audio samples for identifying Romanian dialects.
― 5 min read
Exploring how gestures and expressions enhance our understanding of spoken language.
― 7 min read
A look at mixing music, blending technical skills with artistic vision.
― 5 min read
Exploring new methods in sound detection and localization using synthetic data.
― 5 min read
A new system helps musicians experience sound on a virtual stage.
― 6 min read
New method improves detection of fake audio segments in recordings.
― 5 min read
Computers are learning to separate rhythm and harmony in music for creative applications.
― 4 min read
Microsoft's MuLanTTS offers natural and expressive French text-to-speech capabilities.
― 5 min read
New datasets and methods improve vehicle classification for better traffic management.
― 6 min read
New methods improve accuracy and speed in speech recognition technology.
― 6 min read
A new synthesizer improves the generation of realistic sound effects for media.
― 5 min read
A new approach enhances confidence estimation in ASR systems for better accuracy.
― 4 min read
Introducing a framework for more natural and expressive speech synthesis.
― 6 min read
Learn how technology helps categorize music genres efficiently.
― 6 min read
A unified approach to assess fish feeding using audio and video data.
― 5 min read
A new method improves the creation of emotionally expressive talking-head videos.
― 6 min read
This study explores issues with using convnets for audio filterbank creation.
― 5 min read
The CLAP model bridges audio and text processing for various applications.
― 4 min read
A project aims to improve French speech processing using self-supervised learning.
― 5 min read
New methods improve how machines recognize speech rhythm and emotion.
― 6 min read
A new approach improves sound estimation in spaces with scattering objects.
― 6 min read
Examines how undecidability influences music composition and production today.
― 4 min read
This article explores advancements in speaker diarization using language models for better accuracy.
― 5 min read
This study improves ASR systems' ability to recognize children's speech.
― 5 min read
Researchers explore audio sensing technology for improved pedestrian detection in urban areas.
― 5 min read
New method enhances sound source localization and field separation.
― 6 min read
A new method improves drum sound synthesis by focusing on sharp transient elements.
― 6 min read
Researchers are developing synthetic voice data to protect privacy in voice recognition.
― 5 min read
VoxtLM combines speech recognition, synthesis, text generation, and continuation in one model.
― 4 min read
New system enhances speech recognition using context-aware prompts.
― 4 min read
EnCodecMAE combines self-supervised learning and audio codecs for improved audio task performance.
― 5 min read
A study on using machine learning to identify children's sounds for ASD assessment.
― 5 min read
Introducing a flexible method for recognizing keywords in speech across languages.
― 5 min read
A look at how speech quality is tested using crowdsourcing.
― 5 min read
A new method trains audio captioning systems using only text descriptions.
― 6 min read
A guide to crafting clear and effective academic papers.
― 3 min read
Examining the risks of backdoor attacks on speaker verification systems.
― 6 min read
A new method enhances audio-visual segmentation without detailed labels.
― 5 min read