按年被提到
20242024 · 2 次2026
视觉、语音与图像生成›语音与音频生成·arXiv:2406.05370 · cs.CL

VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers

Sanyuan Chen, Shujie Liu, Long Zhou, Yanqing Liu, Xu Tan, Jinyu Li, Sheng Zhao, Yao Qian, Furu Wei · 2024
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2024-07-10 · 最近 2024-09-17
2不同的人
2活跃月份
2讨论串
46被引(OpenAlex)
arXiv 摘要(候选层不写导读)

This paper introduces VALL-E 2, the latest advancement in neural codec language models that marks a milestone in zero-shot text-to-speech synthesis (TTS), achieving human parity for the first time. Based on its predecessor, VALL-E, the new iteration introduces two significant enhancements: Repetition Aware Sampling refines the original nucleus sampling process by accounting for token repetition in the decoding history. It not only stabilizes the decoding but also circumvents the infinite loop issue. Grouped Code Modeling organizes codec codes into groups to effectively shorten the sequence length, which not only boosts inference speed but also addresses the challenges of long sequence modeling. Our experiments on the LibriSpeech and VCTK datasets show that VALL-E 2 surpasses previous systems in speech robustness, naturalness, and speaker similarity. It is the first of its kind to reach human parity on these benchmarks. Moreover, VALL-E 2 consistently synthesizes high-quality speech, even for sentences that are traditionally challenging due to their complexity or repetitive phrases. The advantages of this work could contribute to valuable endeavors, such as generating speech for individuals with aphasia or people with amyotrophic lateral sclerosis. See https://aka.ms/valle2 for demos of VALL-E 2.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论carapace · 2024-07

“https://arxiv.org/abs/2406.05370 > Our experiments on the LibriSpeech and VCTK datasets show that VALL-E 2 surpasses previous systems in speech robustness, naturalness, and speaker similarity. It is the first of its kind to reach human parity on these benchmarks. Moreover, VALL-E 2 consistently synthesizes high-quality speech, even for sentences that are…”

AI speech generator 'reaches human parity' – but it's too dangerous to release原评论 ↗
评论alephnerd · 2024-09

“> Care to give some examples In the 2010s they were the leader in NLP and the precursor of LLMs like GPT3/3.5/4/4o Machine Translation with Human Parity (2018) - https://arxiv.org/abs/1803.05567 MT-DNN (2019) - https://arxiv.org/abs/1901.11504 MASS (2019) - https://arxiv.org/abs/1905.02450 VALL-E (2023) - https://arxiv.org/abs/2301.02111 VALL-E 2 (2…”

Amazon's Secret Weapon in Chip Design Is Amazon原评论 ↗