A new method enhances general audio models for effective speech recognition.
― 6 min read
Computer Science - Sound
RSSLatest Articles
Latest Articles
A new model brings voice capabilities to devices without internet.
― 5 min read
New model ZET-Speech enhances emotional speech synthesis for diverse speakers.
― 5 min read
Study finds new mixing techniques improve music transcription accuracy.
― 4 min read
A new method enhances machine responses through better emotional understanding.
― 5 min read
A new method improves accuracy in automatic speech recognition for meetings.
― 5 min read
CALLS aims to improve voice assistants' ability to handle customer interactions.
― 5 min read
New methods improve audio restoration and production quality.
― 5 min read
PLCMOS offers a new way to evaluate speech quality without human listeners.
― 5 min read
LoopBoxes helps children create music easily and collaboratively.
― 5 min read
A new method for creating realistic impact sounds through neural networks.
― 5 min read
New technique enhances ASR systems for better recognition of non-native accents.
― 6 min read
New methods leverage speaker identity to improve speech recognition performance.
― 5 min read
A new method combines speech recognition and speaker identification for overlapping speech.
― 5 min read
A novel method improves real-time translation quality and efficiency.
― 4 min read
A new method to estimate room responses in complex sound environments.
― 7 min read
A new method for voice conversion improves clarity and adaptation.
― 6 min read
MeLoDy quickly generates high-quality music from text prompts.
― 5 min read
New methods emerge to protect voice recognition from adversarial attacks.
― 5 min read
A novel technique checks for training data exposure in diffusion models.
― 5 min read
A new model improves voice isolation in noisy environments.
― 5 min read
This article discusses how to recreate magnetic tape sound using digital technology.
― 6 min read
A new method enhances speaker verification by combining knowledge distillation and fine-tuning.
― 6 min read
DeCoR helps machines learn new sounds without forgetting old ones.
― 5 min read
Streaming audio transformers improve speed and efficiency in audio tagging systems.
― 6 min read
New techniques improve accuracy and speed in converting speech to text.
― 5 min read
This research introduces improved assessments for clearer communication in individuals with dysarthria.
― 5 min read
A new method improves speech recognition for names that sound alike.
― 5 min read
A new method enhances the naturalness and variety of text-to-speech output.
― 5 min read
Treff adapter improves audio classification with limited labeled data.
― 5 min read
New methods improve model flexibility and performance in audio tasks.
― 4 min read
Discover how E-PANNs improve sound recognition efficiency.
― 5 min read
This research analyzes dialects using audio recordings to reveal their similarities.
― 6 min read
A novel method enhances audio classification by learning new sounds efficiently.
― 4 min read
New method improves TTS adaptation with minimal data requirements.
― 6 min read
An overview of explainable AI methods in automatic speech recognition.
― 6 min read
A new model improves how machines understand and respond to audio questions.
― 5 min read
Research highlights the need for improved turn-taking in TTS technology.
― 6 min read
A new method improves synthetic speech selection for enhanced ASR system accuracy.
― 6 min read
A new method aligns disfluent speech with text efficiently.
― 5 min read
Improving systems for silent speech recognition with new techniques.
― 5 min read