New methods improve accessibility and accuracy in audio captioning.
― 6 min read
Computer Science - Sound
RSSLearn how to identify fake audio calls with innovative challenge-response techniques.
― 5 min read
CustomListener creates realistic avatars that respond to conversations dynamically.
― 6 min read
Research highlights the importance of timing over specific speaker features in diarization models.
― 6 min read
New method enhances speech synthesis for individuals who cannot speak.
― 6 min read
A look at MONA, a system enhancing silent speech communication.
― 5 min read
An overview of ASR and its advancements in modern applications.
― 4 min read
Exploring new methods to improve speech emotion recognition using natural data.
― 5 min read
Research focuses on helping robots better understand speech amidst background noise.
― 5 min read
This study advances music education by automating the assessment of piano piece difficulty.
― 6 min read
A new benchmark assesses voice recognition systems' performance amidst various disturbances.
― 5 min read
Exploring AI's role in shaping music through advanced techniques and structures.
― 5 min read
A new method enhances speech model performance and efficiency in noisy environments.
― 5 min read
A new method combines traditional techniques with neural networks for better sound localization.
― 5 min read
A novel approach to enhance acoustic sensing without compromising audio quality.
― 6 min read
A new system improves realistic gesture creation using only speech audio.
― 6 min read
Notochord enhances real-time MIDI music creation using AI for richer performances.
― 6 min read
A method for more intuitive control over singing voices using natural language prompts.
― 7 min read
New model emoDARTS improves accuracy in recognizing speech emotions using deep learning.
― 6 min read
A study on improving TTS systems with diverse voice samples.
― 4 min read
New tools enhance voice recording editing and production quality.
― 5 min read
New models enhance duet interactions in virtual dance performances.
― 6 min read
Discover how generative equalization breathes new life into old music recordings.
― 7 min read
Research identifies and classifies Sorani Kurdish dialects using extensive audio recordings.
― 6 min read
A new method improves sound processing through automatic tuning of Feedback Delay Networks.
― 6 min read
A new method improves speech evaluation using entire recordings.
― 7 min read
A new approach to evaluate how well music follows audio prompts.
― 8 min read
A new dataset improves how robots interpret real-world environments.
― 6 min read
This method improves audio separation by combining language descriptions with sound analysis.
― 6 min read
UniAV combines action localization, sound detection, and audio-visual event localization for better video understanding.
― 7 min read
CLaM-TTS improves speech synthesis using advanced techniques for better efficiency and quality.
― 6 min read
Graphs allow for new insights into music structure and relationships.
― 5 min read
RALL-E enhances text-to-speech synthesis for clearer, more natural speech.
― 5 min read
Exploring machine learning techniques for modeling analog audio effects.
― 6 min read
MuPT utilizes ABC notation for effective music generation with AI.
― 5 min read
New methods improve audio representation through self-supervised learning techniques.
― 6 min read
A method using AI enhances sound representation in various environments.
― 6 min read
Explore the role of spectral moments in reverberation chamber testing and the impact of noise.
― 5 min read
A new system for accurate and lightweight real-time piano transcription.
― 5 min read
A new framework enhances AI's grasp of 3D spaces.
― 7 min read