English
Related papers

Related papers: Selective Classifier-free Guidance for Zero-shot T…

200 papers

Zero-shot cross-lingual transfer is when a multilingual model is trained to perform a task in one language and then is applied to another language. Although the zero-shot cross-lingual transfer approach has achieved success in various…

Computation and Language · Computer Science 2023-05-30 Tianjian Li , Kenton Murray

Typical methods for text-to-image synthesis seek to design effective generative architecture to model the text-to-image mapping directly. It is fairly arduous due to the cross-modality translation. In this paper we circumvent this problem…

Computer Vision and Pattern Recognition · Computer Science 2020-07-14 Jiadong Liang , Wenjie Pei , Feng Lu

Conventional text-to-speech (TTS) research has predominantly focused on enhancing the quality of synthesized speech for speakers in the training dataset. The challenge of synthesizing lifelike speech for unseen, out-of-dataset speakers,…

Sound · Computer Science 2024-04-30 Wenbin Wang , Yang Song , Sanjay Jha

In recent years, several text-to-speech systems have been proposed to synthesize natural speech in zero-shot, few-shot, and low-resource scenarios. However, these methods typically require training with data from many different speakers.…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-03 Kishor Kayyar Lakshminarayana , Frank Zalkow , Christian Dittmar , Nicola Pia , Emanuel A. P. Habets

Adding additional control to pretrained diffusion models has become an increasingly popular research area, with extensive applications in computer vision, reinforcement learning, and AI for science. Recently, several studies have proposed…

Machine Learning · Computer Science 2024-05-30 Yifei Shen , Xinyang Jiang , Yezhen Wang , Yifan Yang , Dongqi Han , Dongsheng Li

Text-to-image diffusion models have achieved remarkable performance in image synthesis, while the text interface does not always provide fine-grained control over certain image factors. For instance, changing a single token in the text can…

Computer Vision and Pattern Recognition · Computer Science 2024-02-22 Chen Wu , Fernando De la Torre

Classifier-Free Guidance (CFG) is essential for high-fidelity conditional generation in flow matching, yet it imposes significant computational overhead by requiring dual forward passes at each sampling step. In this work, we address this…

Artificial Intelligence · Computer Science 2026-05-08 Xin Peng , Ang Gao

The CLIP model has demonstrated significant advancements in aligning visual and language modalities through large-scale pre-training on image-text pairs, enabling strong zero-shot classification and retrieval capabilities on various…

Computer Vision and Pattern Recognition · Computer Science 2025-03-24 Gensheng Pei , Tao Chen , Yujia Wang , Xinhao Cai , Xiangbo Shu , Tianfei Zhou , Yazhou Yao

The zero-shot scenario for speech generation aims at synthesizing a novel unseen voice with only one utterance of the target speaker. Although the challenges of adapting new voices in zero-shot scenario exist in both stages -- acoustic…

Sound · Computer Science 2022-07-06 Yi Lei , Shan Yang , Jian Cong , Lei Xie , Dan Su

Diffusion models have achieved remarkable progress in image and audio generation, largely due to Classifier-Free Guidance. However, the choice of guidance scale remains underexplored: a fixed scale often fails to generalize across prompts…

Sound · Computer Science 2025-10-07 Xuanhao Zhang , Chang Li

Voice Conversion research in recent times has increasingly focused on improving the zero-shot capabilities of existing methods. Despite remarkable advancements, current architectures still tend to struggle in zero-shot cross-lingual…

Sound · Computer Science 2025-05-26 Advait Joglekar , Divyanshu Singh , Rooshil Rohit Bhatia , S. Umesh

Diffusion models achieve strong performance in generative modeling, but their success often relies heavily on classifier-free guidance (CFG), an inference-time heuristic that modifies the sampling trajectory. In theory, diffusion models…

Machine Learning · Computer Science 2026-05-14 Xiang Li , Yixuan Jia , Xiao Li , Jeffrey A. Fessler , Rongrong Wang , Qing Qu

Text classifiers have promising applications in high-stake tasks such as resume screening and content moderation. These classifiers must be fair and avoid discriminatory decisions by being invariant to perturbations of sensitive attributes…

Computation and Language · Computer Science 2023-03-17 Florian E. Dorner , Momchil Peychev , Nikola Konstantinov , Naman Goel , Elliott Ash , Martin Vechev

Recent studies show that simple training-free techniques can dramatically improve the quality of text-to-2D generation outputs, e.g. Classifier-Free Guidance (CFG) or FreeU. However, these training-free techniques have been underexplored in…

Computer Vision and Pattern Recognition · Computer Science 2025-05-28 Junhong Lee , Seungwook Kim , Minsu Cho

To guarantee that an LLM's outputs conform to a specified structure, context-free grammar (CFG) decoding engines force the selection of next tokens that produce strings that conform to a given CFG. While current CFG-constrained decoding…

Artificial Intelligence · Computer Science 2026-05-29 Michael Sullivan , Alexander Koller

Recent progress in large-scale zero-shot speech synthesis has been significantly advanced by language models and diffusion models. However, the generation process of both methods is slow and computationally intensive. Efficient speech…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-25 Zhen Ye , Zeqian Ju , Haohe Liu , Xu Tan , Jianyi Chen , Yiwen Lu , Peiwen Sun , Jiahao Pan , Weizhen Bian , Shulin He , Wei Xue , Qifeng Liu , Yike Guo

The potential of synthetic data in text-to-speech (TTS) model training has gained increasing attention, yet its rationality and effectiveness require systematic validation. In this study, we systematically investigate the feasibility of…

Sound · Computer Science 2025-12-22 Tingxiao Zhou , Leying Zhang , Zhengyang Chen , Yanmin Qian

Text-to-image diffusion models have recently received a lot of interest for their astonishing ability to produce high-fidelity images from text only. However, achieving one-shot generation that aligns with the user's intent is nearly…

Computer Vision and Pattern Recognition · Computer Science 2023-11-06 Manuel Brack , Felix Friedrich , Dominik Hintersdorf , Lukas Struppek , Patrick Schramowski , Kristian Kersting

Natural Language Generation (NLG) accepts input data in the form of images, videos, or text and generates corresponding natural language text as output. Existing NLG methods mainly adopt a supervised approach and rely heavily on coupled…

Computation and Language · Computer Science 2024-06-04 Bang Yang , Fenglin Liu , Yuexian Zou , Xian Wu , Yaowei Wang , David A. Clifton

Zero-shot Text-to-Speech (TTS) has recently advanced significantly, enabling models to synthesize speech from text using short, limited-context prompts. These prompts serve as voice exemplars, allowing the model to mimic speaker identity,…

Sound · Computer Science 2025-10-06 Hieu-Nghia Huynh-Nguyen , Huynh Nguyen Dang , Ngoc-Son Nguyen , Van Nguyen