新的TTS模型实现更低延迟和改进的语音-文本对齐 · 跟踪4个来源

报道来源 [6]

1. arXiv cs.CL TIER_1 English(EN) · Roman Koshkin, Jeon Haesung, Lianbo Liu, Hao Shi, Mengjie Zhao, Yusuke Fujita, Yui Sudo · 2026-09-11 04:00

   通过语音转文本因果对齐实现流式翻译和转录

   arXiv:2603.11578v2 Announce Type: replace Abstract: Simultaneous machine translation (SiMT) has traditionally relied on offline machine translation models coupled with human-engineered heuristics or learned policies. We propose Hikari, a policy-free, end-to-end model for simultan…

2. arXiv cs.AI TIER_1 English(EN) · Hanwen Liu, Saierdaer Yusuyin, Hao Huang, Zhijian Ou · 2026-09-10 04:00

   CTC-TTS：基于LLM的双流式文本到语音转换及CTC对齐

   arXiv:2602.19574v2 Announce Type: replace-cross Abstract: Large-language-model (LLM)-based text-to-speech (TTS) systems can generate natural speech, but most are not designed for low-latency dual-streaming synthesis. High-quality dual-streaming TTS depends on accurate text--speec…

3. arXiv cs.CL TIER_1 English(EN) · Kang-wook Kim, Jinyoung Park, Jinsoo Kim, Sehun Lee, Sang Hoon Woo, Gunhee Kim · 2026-09-10 04:00

   StreamAlign：流式文本对齐语音分词

   arXiv:2609.09719v1 Announce Type: new Abstract: Text-aligned speech tokenization methods have emerged to better align speech tokens with LLM token spaces, enabling more effective utilization of pretrained LLMs. However, they rely on offline automatic speech recognition (ASR), lea…

4. arXiv cs.LG TIER_1 English(EN) · Fritz Cremer, Jonathan Cremer · 2026-09-10 04:00

   TontaubeV1：采用分层编解码器建模和有界上下文的流式文本到语音转换

   arXiv:2609.08703v1 Announce Type: cross Abstract: Text-to-speech systems often face a trade-off between natural prosody and efficient inference: higher perceptual quality typically comes at increased computational cost and latency. We present TontaubeV1, a model that preserves na…

5. Hugging Face Daily Papers TIER_1 English(EN) · 2026-09-09 05:03

   StreamAlign：流式文本对齐语音分词

   Text-aligned speech tokenization methods have emerged to better align speech tokens with LLM token spaces, enabling more effective utilization of pretrained LLMs. However, they rely on offline automatic speech recognition (ASR), leading to two key limitations: (i) the need for co…

6. Hugging Face Daily Papers TIER_1 English(EN) · 2026-09-08 13:03

   TontaubeV1：具有分层编解码器建模和有界上下文的流式文本到语音转换

   Text-to-speech systems often face a trade-off between natural prosody and efficient inference: higher perceptual quality typically comes at increased computational cost and latency. We present TontaubeV1, a model that preserves natural prosody while enabling streaming from a sing…