Yi Ren

Affiliations

University of British Columbia

papers

529

total citations

papers (13)

GenerSpeech: Towards Style Transfer for Generalizable Out-Of-Domain Text-to-Speech

NEURIPS 2022arXiv

citations

Tensor Normal Training for Deep Learning Models

NEURIPS 2021arXiv

citations

Emotion Rendering for Conversational Speech Synthesis with Heterogeneous Graph-Based Context Modeling

AAAI 2024arXiv

citations

Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective

NEURIPS 2023arXiv

citations

AMD: Autoregressive Motion Diffusion

AAAI 2024arXiv

citations

Improving Compositional Generalization using Iterated Learning and Simplicial Embeddings

NEURIPS 2023arXiv

citations

Dict-TTS: Learning to Pronounce with Prior Dictionary Knowledge for Text-to-Speech

NEURIPS 2022arXiv

citations

State-Constrained Zero-Sum Differential Games with One-Sided Information

ICML 2024arXiv

citations

M4Singer: A Multi-Style, Multi-Singer and Musical Score Provided Mandarin Singing Corpus

NEURIPS 2022

citations

Yi Ren

Affiliations

papers (13)

Practical Quasi-Newton Methods for Training Deep Neural Networks

PortaSpeech: Portable and High-Quality Generative Text-to-Speech

Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis

Learning Dynamics of LLM Finetuning

GenerSpeech: Towards Style Transfer for Generalizable Out-Of-Domain Text-to-Speech

Tensor Normal Training for Deep Learning Models

Emotion Rendering for Conversational Speech Synthesis with Heterogeneous Graph-Based Context Modeling

Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective

AMD: Autoregressive Motion Diffusion

Improving Compositional Generalization using Iterated Learning and Simplicial Embeddings

Dict-TTS: Learning to Pronounce with Prior Dictionary Knowledge for Text-to-Speech

State-Constrained Zero-Sum Differential Games with One-Sided Information

M4Singer: A Multi-Style, Multi-Singer and Musical Score Provided Mandarin Singing Corpus

papers (13)

Practical Quasi-Newton Methods for Training Deep Neural Networks

PortaSpeech: Portable and High-Quality Generative Text-to-Speech

Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis

Learning Dynamics of LLM Finetuning

GenerSpeech: Towards Style Transfer for Generalizable Out-Of-Domain Text-to-Speech

Tensor Normal Training for Deep Learning Models

Emotion Rendering for Conversational Speech Synthesis with Heterogeneous Graph-Based Context Modeling

Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective

AMD: Autoregressive Motion Diffusion

Improving Compositional Generalization using Iterated Learning and Simplicial Embeddings

Dict-TTS: Learning to Pronounce with Prior Dictionary Knowledge for Text-to-Speech

State-Constrained Zero-Sum Differential Games with One-Sided Information

M4Singer: A Multi-Style, Multi-Singer and Musical Score Provided Mandarin Singing Corpus