We have 4 of 14 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
KOMOS is proposed, a Korean MOS predictor for evaluating the overall quality of both read and spontaneous speech, and achieves an utterance-level Spearman rank correlation (SRCC) of 0.900.
An acoustic-to-text KV compression, which introduces a transcription side channel to convert incoming speech into compact textual memory within this interval, which reduces peak streaming KV-cache size and improves transcription, temporal question answering, and summarization over the baseline.
GUARD is proposed, a lightweight speaker identity unlearning framework that combines a learned speaker gate with speaker-agnostic activation steering on a frozen TTS backbone that demonstrates that similarity reduction alone may not fully characterize successful speaker identity unlearning and highlights re-identificat...
DELTA-TTS is introduced, a lightweight LoRA-based adaptation framework that converts a pretrained AR TTS model into a discrete diffusion language model (dLLM) for confidence-ordered speech-token decoding and produces sharper text--speech alignment, increases overall decoding confidence, and mitigates the hallucinations...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
