New methods improve human-robot conversation by enhancing speech clarity.
― 5 min read
Electrical Engineering and Systems Science - Audio and Speech Processing
RSSNew methods improve access to spoken news by segmenting topics more effectively.
― 6 min read
This research analyzes Mamba's performance in speech tasks, emphasizing sound reconstruction and recognition.
― 5 min read
A new method for music tagging using few-shot learning shows promising results.
― 6 min read
FlowSep introduces a fresh method for extracting sounds using language queries.
― 5 min read
SSR-Speech offers new solutions for speech generation and editing.
― 5 min read
Advancements in AI make fake audio common, prompting the need for detection.
― 6 min read
New model enhances speech generation in diverse dialects of pitch-accent languages.
― 5 min read
A new method improves sound localization accuracy while ensuring data privacy.
― 4 min read
A new method for creating structured pop music using graph-based techniques.
― 6 min read
A new method for improving keyword spotting while retaining learned knowledge.
― 5 min read
Researchers develop a dataset to improve speech recognition and analysis techniques.
― 6 min read
SoloAudio improves sound extraction using advanced techniques and synthetic data.
― 5 min read
OpenACE provides a fair benchmark for assessing audio codecs across various conditions.
― 5 min read
A method to identify faults in electric motors through sound analysis and Bayesian neural networks.
― 5 min read
Speech recognition models are evolving with multi-token prediction for faster responses.
― 5 min read
Efforts to improve speech technology for the under-resourced Faetar language.
― 5 min read
A new zero-shot method enhances voice conversion accuracy and minimizes sound leakage.
― 5 min read
Study reveals how tones change in everyday Taiwanese Mandarin speech.
― 5 min read
New method improves detection of Parkinson's Disease through speech analysis with advanced technology.
― 5 min read
New approach enhances voice isolation in mixed audio settings using discrete tokens.
― 5 min read
Research links paintings to music by interpreting emotions.
― 6 min read
A study on using language models for correcting errors in speech recognition systems.
― 5 min read
FLAMO simplifies audio processing through differentiable techniques and frequency-sampling.
― 6 min read
A new method enhances the automatic detection of speech issues linked to Parkinson's disease.
― 4 min read
A new approach enhances ASR systems for better classroom communication.
― 5 min read
This article explores how varied inputs can boost speech recognition accuracy.
― 5 min read
A system making music creation easy and accessible for all skill levels.
― 6 min read
ReCLAP enhances audio classification with detailed prompts for better accuracy.
― 5 min read
A project aims to improve speech technology for those with communication challenges.
― 5 min read
MambaFoley revolutionizes Foley sound synthesis with improved timing and realism.
― 5 min read
A new system enhances accent accuracy in TTS for better communication.
― 5 min read
Using CLAP embeddings enhances music recommendation systems significantly.
― 6 min read
Study explores ASR development for Amis and Seediq, focusing on data use.
― 7 min read
LLaQo offers detailed feedback for music performance assessment, enhancing student learning.
― 5 min read
Researchers develop new strategies for distinguishing individual animals using their unique sounds.
― 5 min read
A new method simplifies siren detection for enhanced vehicle safety.
― 5 min read
A new approach combines sound event detection and speaker diarization for better audio understanding.
― 5 min read
A new approach enhances ASR by focusing on specific speaker details.
― 5 min read
A study revealing how deep learning models recognize emotions in speech.
― 5 min read