中文
相关论文

相关论文: CoVoMix2: Advancing Zero-Shot Dialogue Generation …

200 篇论文

Large speech generation models are evolving from single-speaker, short sentence synthesis to multi-speaker, long conversation geneartion. Current long-form speech generation models are predominately constrained to dyadic, turn-based…

We introduce a zero-shot video captioning method that employs two frozen networks: the GPT-2 language model and the CLIP image-text matching model. The matching score is used to steer the language model toward generating a sentence that has…

计算机视觉与模式识别 · 计算机科学 2022-07-29 Yoad Tewel , Yoav Shalev , Roy Nadler , Idan Schwartz , Lior Wolf

Zero-shot voice conversion aims to transfer the voice of a source speaker to that of a speaker unseen during training, while preserving the content information. Although various methods have been proposed to reconstruct speaker information…

声音 · 计算机科学 2024-08-22 Anastasia Avdeeva , Aleksei Gusev

People naturally conduct spontaneous body motions to enhance their speeches while giving talks. Body motion generation from speech is inherently difficult due to the non-deterministic mapping from speech to body motions. Most existing works…

计算机视觉与模式识别 · 计算机科学 2022-03-07 Jing Xu , Wei Zhang , Yalong Bai , Qibin Sun , Tao Mei

Text-to-video is a rapidly growing research area that aims to generate a semantic, identical, and temporal coherence sequence of frames that accurately align with the input text prompt. This study focuses on zero-shot text-to-video…

计算机视觉与模式识别 · 计算机科学 2023-09-27 Hanzhuo Huang , Yufan Feng , Cheng Shi , Lan Xu , Jingyi Yu , Sibei Yang

Recent efforts in Dialogue State Tracking (DST) for task-oriented dialogues have progressed toward open-vocabulary or generation-based approaches where the models can generate slot value candidates from the dialogue history itself. These…

计算与语言 · 计算机科学 2020-02-25 Hung Le , Richard Socher , Steven C. H. Hoi

Audio is inherently temporal and closely synchronized with the visual world, making it a naturally aligned and expressive control signal for controllable video generation (e.g., movies). Beyond control, directly translating audio into video…

计算机视觉与模式识别 · 计算机科学 2025-06-10 Shuchen Weng , Haojie Zheng , Zheng Chang , Si Li , Boxin Shi , Xinlong Wang

We introduce VoxRAG, a modular speech-to-speech retrieval-augmented generation system that bypasses transcription to retrieve semantically relevant audio segments directly from spoken queries. VoxRAG employs silence-aware segmentation,…

信息检索 · 计算机科学 2025-08-08 Zackary Rackauckas , Julia Hirschberg

Recent developments in voice cloning and talking head generation demonstrate impressive capabilities in synthesizing natural speech and realistic lip synchronization. Current methods typically require and are trained on large scale datasets…

声音 · 计算机科学 2025-09-17 Javeria Amir , Farwa Attaria , Mah Jabeen , Umara Noor , Zahid Rashid

We demonstrate substantial performance gains in zero-shot dialogue state tracking (DST) by enhancing training data diversity through synthetic data generation. Existing DST datasets are severely limited in the number of application domains…

计算与语言 · 计算机科学 2024-06-14 James D. Finch , Jinho D. Choi

The majority of current systems for end-to-end dialog generation focus on response quality without an explicit control over the affective content of the responses. In this paper, we present an affect-driven dialog system, which generates…

计算与语言 · 计算机科学 2019-04-08 Pierre Colombo , Wojciech Witon , Ashutosh Modi , James Kennedy , Mubbasir Kapadia

Most current zero-shot voice conversion methods rely on externally supervised components, particularly speaker encoders, for training. To explore alternatives that eliminate this dependency, this paper introduces GenVC, a novel framework…

音频与语音处理 · 电气工程与系统科学 2025-08-21 Zexin Cai , Henry Li Xinyuan , Ashi Garg , Leibny Paola García-Perera , Kevin Duh , Sanjeev Khudanpur , Matthew Wiesner , Nicholas Andrews

Creating music is iterative, requiring varied methods at each stage. However, existing AI music systems fall short in orchestrating multiple subsystems for diverse needs. To address this gap, we introduce Loop Copilot, a novel system that…

声音 · 计算机科学 2024-09-02 Yixiao Zhang , Akira Maezawa , Gus Xia , Kazuhiko Yamamoto , Simon Dixon

End-to-end speech-to-speech translation (S2ST) systems typically struggle with a critical data bottleneck: the scarcity of parallel speech-to-speech corpora. To overcome this, we introduce RosettaSpeech, a novel zero-shot framework trained…

音频与语音处理 · 电气工程与系统科学 2026-02-17 Zhisheng Zheng , Xiaohang Sun , Tuan Dinh , Abhishek Yanamandra , Abhinav Jain , Zhu Liu , Sunil Hadap , Vimal Bhat , Manoj Aggarwal , Gerard Medioni , David Harwath

Recent text-to-video generation approaches rely on computationally heavy training and require large-scale video datasets. In this paper, we introduce a new task of zero-shot text-to-video generation and propose a low-cost approach (without…

计算机视觉与模式识别 · 计算机科学 2023-03-24 Levon Khachatryan , Andranik Movsisyan , Vahram Tadevosyan , Roberto Henschel , Zhangyang Wang , Shant Navasardyan , Humphrey Shi

Recent advancements in large scale text-to-image models have opened new possibilities for guiding the creation of images through human-devised natural language. However, while prior literature has primarily focused on the generation of…

计算机视觉与模式识别 · 计算机科学 2023-02-09 Hyeonho Jeong , Gihyun Kwon , Jong Chul Ye

Whispered-to-normal (W2N) speech conversion aims to reconstruct missing phonation from whispered input while preserving content and speaker identity. This task is challenging due to temporal misalignment between whisper and voiced…

音频与语音处理 · 电气工程与系统科学 2026-03-05 Fabian Ritter-Gutierrez , Md Asif Jalal , Pablo Peso Parada , Karthikeyan Saravanan , Yusun Shul , Minseung Kim , Gun-Woo Lee , Han-Gil Moon

In this paper we propose Flowtron: an autoregressive flow-based generative network for text-to-speech synthesis with control over speech variation and style transfer. Flowtron borrows insights from IAF and revamps Tacotron in order to…

声音 · 计算机科学 2020-07-17 Rafael Valle , Kevin Shih , Ryan Prenger , Bryan Catanzaro

Language models trained on large-scale corpora can generate remarkably fluent results in open-domain dialogue. However, for the persona-based dialogue generation task, consistency and coherence are also key factors, which are great…

人工智能 · 计算机科学 2023-05-23 Junkai Zhou , Liang Pang , Huawei Shen , Xueqi Cheng

We present VoiceRestore, a novel approach to restoring the quality of speech recordings using flow-matching Transformers trained in a self-supervised manner on synthetic data. Our method tackles a wide range of degradations frequently found…

音频与语音处理 · 电气工程与系统科学 2025-01-03 Stanislav Kirdey