{"total":29,"rows":[{"id":"2106.10132","title":"VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice Conversion","created":"2021-06-18","cited_by_count":64,"area":null},{"id":"2212.09730","title":"Speaking Style Conversion in the Waveform Domain Using Discrete Self-Supervised Units","created":"2022-12-19","cited_by_count":15,"area":null},{"id":"2305.03256","title":"Stylized Data-to-Text Generation: A Case Study in the E-Commerce Domain","created":"2023-05-05","cited_by_count":11,"area":null},{"id":"2202.13277","title":"Learning the Beauty in Songs: Neural Singing Voice Beautifier","created":"2022-02-27","cited_by_count":10,"area":null},{"id":"2310.16334","title":"Structured Multi-Track Accompaniment Arrangement via Style Prior Modelling","created":"2023-10-25","cited_by_count":9,"area":null},{"id":"2404.08857","title":"Voice Attribute Editing with Text Prompt","created":"2024-04-13","cited_by_count":9,"area":null},{"id":"2309.09470","title":"Face-Driven Zero-Shot Voice Conversion with Memory-based Face-Voice Alignment","created":"2023-09-18","cited_by_count":8,"area":null},{"id":"2107.06642","title":"Many-to-Many Voice Conversion based Feature Disentanglement using Variational Autoencoder","created":"2021-07-11","cited_by_count":7,"area":null},{"id":"2112.04424","title":"Training Robust Zero-Shot Voice Conversion Models with Self-supervised Features","created":"2021-12-08","cited_by_count":7,"area":null},{"id":"2112.14478","title":"Semantic Feature Extraction for Generalized Zero-shot Learning","created":"2021-12-29","cited_by_count":7,"area":null},{"id":"2205.04093","title":"So Different Yet So Alike! Constrained Unsupervised Text Style Transfer","created":"2022-05-09","cited_by_count":7,"area":null},{"id":"2206.02512","title":"Unsupervised TTS Acoustic Modeling for TTS with Conditional Disentangled Sequential VAE","created":"2022-06-06","cited_by_count":7,"area":null},{"id":"2202.12307","title":"Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graph","created":"2022-02-24","cited_by_count":6,"area":null},{"id":"2111.03811","title":"SIG-VC: A Speaker Information Guided Zero-shot Voice Conversion System for Both Human Beings and Machines","created":"2021-11-06","cited_by_count":5,"area":null},{"id":"2308.10262","title":"Learning Disentangled Representation with Mutual Information Maximization for Real-Time UAV Tracking","created":"2023-08-20","cited_by_count":5,"area":null},{"id":"2202.02751","title":"Tubes Among Us: Analog Attack on Automatic Speaker Identification","created":"2022-02-06","cited_by_count":3,"area":null},{"id":"2211.07343","title":"Replacing Language Model for Style Transfer","created":"2022-11-14","cited_by_count":3,"area":null},{"id":"2307.09435","title":"SLMGAN: Exploiting Speech Language Model Representations for Unsupervised Zero-Shot Voice Conversion in GANs","created":"2023-07-18","cited_by_count":3,"area":null},{"id":"2205.04952","title":"Read the Room: Adapting a Robot's Voice to Ambient and Social Contexts","created":"2022-05-10","cited_by_count":2,"area":null},{"id":"2202.13363","title":"Variational Autoencoder with Disentanglement Priors for Low-Resource Task-Specific Natural Language Generation","created":"2022-02-27","cited_by_count":1,"area":null},{"id":"2203.16037","title":"Enhancing Zero-Shot Many to Many Voice Conversion with Self-Attention VAE","created":"2022-03-30","cited_by_count":1,"area":null},{"id":"2403.03704","title":"Causal Prototype-inspired Contrast Adaptation for Unsupervised Domain Adaptive Semantic Segmentation of High-resolution Remote Sensing Imagery","created":"2024-03-06","cited_by_count":1,"area":null},{"id":"2410.03192","title":"MultiVerse: Efficient and Expressive Zero-Shot Multi-Task Text-to-Speech","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2107.12346","title":"Beyond Voice Identity Conversion: Manipulating Voice Attributes by Adversarial Learning of Structured Disentangled Representations","created":"2021-07-26","cited_by_count":0,"area":null},{"id":"2110.09928","title":"CycleFlow: Purify Information Factors by Cycle Loss","created":"2021-10-18","cited_by_count":0,"area":null},{"id":"2306.03421","title":"Diversifying Joint Vision-Language Tokenization Learning","created":"2023-06-06","cited_by_count":0,"area":null},{"id":"2406.02699","title":"Operational Latent Spaces","created":"2024-06-04","cited_by_count":0,"area":null},{"id":"2511.12074","title":"MF-Speech: Achieving Fine-Grained and Compositional Control in Speech Generation via Factor Disentanglement","created":"2025-11-15","cited_by_count":0,"area":null},{"id":"2607.17264","title":"Coordinated Disentanglement with Iterative Mode Discovery Under Hidden Correlations","created":"2026-07-19","cited_by_count":0,"area":null}],"next_cursor":null}