A new approach improves sound estimation in spaces with scattering objects.
― 6 min read
Hiroshi Saruwatari
Core-set selection improves text-to-speech models by focusing on diverse data.
― 5 min read
This study examines if learned speech symbols mimic word frequency patterns.
― 5 min read
Coco-Nut offers diverse Japanese voice samples for advanced text-to-speech applications.
― 10 min read
A study on improving TTS systems with diverse voice samples.
― 4 min read
RALL-E enhances text-to-speech synthesis for clearer, more natural speech.
― 5 min read
Introducing spatial voice conversion to enhance audio realism and immersion.
― 6 min read
J-CHAT provides a large, open-source dataset for enhancing spoken dialogue systems.
― 5 min read
Researchers develop SaSLaW to enhance machine speech adaptation in various environments.
― 5 min read
BigCodec improves sound quality in low-bitrate audio transmission.
― 4 min read
New model enhances speech generation in diverse dialects of pitch-accent languages.
― 5 min read
A new system predicts naturalness scores for synthetic speech using innovative methods.
― 5 min read
A new method enhances synthesized ensemble singing by modeling singer interactions.
― 5 min read