In a significant leap forward for audio synthesis, researchers have introduced UniMoE-Audio, a groundbreaking model that unifies speech and music generation within a dynamic framework, promising to revolutionize the way we create and interact with so
In a significant stride towards enhancing speech technology, researchers have unveiled LongCat-Audio-Codec, an innovative audio tokenizer and detokenizer solution tailored for industrial-grade, end-to-end speech large language models. This breakthrou
In a significant stride towards enhancing communication for individuals with dysarthria, researchers have introduced a novel approach to data augmentation that promises to revolutionize dysarthric speech recognition (DSR) systems. This breakthrough a
