6 papers
CuteTTS: Efficient and High-Quality Speech Synthesis via Autoregressive Modeling of Continuous Latents
Yuqian Zhang, Yao Shi, Kexin Huang +6
Zero-shot text-to-speech (TTS) now supports interactive assistants, personalized media, and accessibility tools. All TTS systems require faithful linguistic rendering, consistent s…
MOSS-VoiceGenerator: Create Realistic Voices with Natural Language Descriptions
Kexin Huang, Liwei Fan, Botian Jiang +11
Voice design from natural language aims to generate speaker timbres directly from free-form textual descriptions, allowing users to create voices tailored to specific roles, person…
MOSS-TTSD: Text to Spoken Dialogue Generation
Yuqian Zhang, Donghua Yu, Zhengyuan Lin +15
Spoken dialogue generation is crucial for applications like podcasts, dynamic commentary, and entertainment content, but poses significant challenges compared to single-utterance t…
MOSS-TTS Technical Report
Yitian Gong, Botian Jiang, Yiwei Zhao +23
This technical report presents MOSS-TTS, a speech generation foundation model built on a scalable recipe: discrete audio tokens, autoregressive modeling, and large-scale pretrainin…
Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generation
Zeqi Xiao, Yiwei Zhao, Lingxiao Li +6
We investigate whether video generative models can exhibit visuospatial intelligence, a capability central to human cognition, using only visual data. To this end, we present Video…
Correctness-Guaranteed Code Generation via Constrained Decoding
Lingxiao Li, Salar Rahili, Yiwei Zhao
Language Models (LMs) are increasingly being used for code generation, but ensuring the correctness of generated programs remains a significant challenge. Although imperfect code m…