A dataset of home sounds promotes safety and comfort for older adults.
― 5 min read
Computer Science - Sound
RSSSD-Codec improves audio processing by separating different sound types effectively.
― 5 min read
This article discusses methods to enhance speech recognition for accented speech.
― 6 min read
A new approach enhances the interpretability of spoof speech detection.
― 5 min read
A look at the new single-stage TTS system improving speech generation.
― 6 min read
This study addresses challenges in audio language models for low-resource languages.
― 5 min read
This study enhances emotion recognition systems for less common languages using high-resource data.
― 6 min read
A model improves speech tasks in multilingual settings, addressing code-switching challenges.
― 5 min read
DeFT-Mamba improves sound separation and classification in noisy environments.
― 5 min read
CADA-GAN enhances ASR systems' performance across various recording environments.
― 6 min read
EVA combines audio and visual signals for better speech recognition accuracy.
― 4 min read
A new framework simplifies speech recognition in busy environments.
― 5 min read
Llama-AVSR merges audio and visual inputs for enhanced speech recognition accuracy.
― 6 min read
WMCodec enhances audio watermarking for better security and authenticity.
― 5 min read
New models tackle sound classification with limited training data.
― 5 min read
A new approach improves fake audio detection using pretrained models.
― 5 min read
New method improves speech generation quality and efficiency.
― 4 min read
A method combining labeled and unlabeled data enhances sound source detection.
― 5 min read
Discover how audio cues aid players in table tennis.
― 6 min read
A system prioritizing melody while offering control over orchestral music generation.
― 5 min read
A new method uses virtual shadowing to enhance language learners' pronunciation feedback.
― 6 min read
New methods improve binaural audio quality in challenging sound environments.
― 8 min read
A new ASR method helps technology understand children's speech better.
― 5 min read
Composer uses text prompts to create complex music compositions in MIDI format.
― 5 min read
A resource for studying singing patterns in Japanese idol music.
― 6 min read
ViolinDiff enhances the realism of computer-generated violin music.
― 5 min read
Combining features enhances underwater sound classification accuracy.
― 6 min read
Transfer learning improves audio classification for underwater sound detection.
― 6 min read
A new model creates audio that matches video, enhancing media experiences.
― 4 min read
A method to boost automatic speech recognition by blending keyword lists with language models.
― 4 min read
A study on vocal imitation techniques using technology to enhance communication.
― 5 min read
Learn how to effectively train speech models with fewer labeled resources.
― 7 min read
An analysis of gender terminology in speech technology and its societal implications.
― 7 min read
A new framework improves detection of overlapping sound events in complex audio environments.
― 6 min read
Research on improving bird sound identification through machine learning techniques.
― 6 min read
A new method improves automatic piano cover creation using existing music transcription technology.
― 6 min read
A look at the Codec-SUPERB challenge results and codec performance metrics.
― 5 min read
MultiMed project enhances automatic speech recognition for better healthcare communication.
― 5 min read
A fresh approach to audio quality assessment without needing clean references.
― 6 min read
ECHO framework improves sound classification accuracy using structured labels and a two-stage learning process.
― 5 min read