Accent Analogy Guidance: More Speaker Similarity at Equal Accent in Cross-Lingual Voice Cloning

arXiv:2609.29123 · cs.SD, cs.CL, eess.AS · Submitted 2026-09-24 · Read on arXiv

cs.SD, cs.CL, eess.AS

Submitted: 2026-09-24

Updated: 2026-09-24

Comments: 5 pages, 1 figure, 2 tables. Submitted to ICASSP 2027. Listening samples: https://yoomee-cho.github.io/accent-analogy-guidance/

Project page: https://yoomee-cho.github.io/accent-analogy-guidance

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Flow Matching — 3× in this paper · explained in 8 episodes
• AUC — 2× in this paper · explained in 2 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• LLM judge — 2× in this paper · explained in 2 episodes
• Steering — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Activation Addition — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Diffusion Model — 1× in this paper · explained in 8 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models
• Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling
• X-Voice: Enabling Everyone to Speak 30 Languages via Zero-Shot Cross-Lingual Voice Cloning
• THCHS-30 : A Free Chinese Speech Corpus
• Classifier-Free Diffusion Guidance
• MegaTTS 3: Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesis
• Selective Classifier-free Guidance for Zero-shot Text-to-speech
• Seed-TTS: A Family of High-Quality Versatile Speech Generation Models
• Joint Residual Reweighting for Classifier Free Guidance in Flow-Matching Zero-Shot TTS
• Phrase-Localized Language-Contrastive Guidance: Training-Free Localized Accent Control for Code-Switching Text-to-Speech
• CrossAccent-TTS: Cross-Lingual Accent-Intensity Controllable Text-to-Speech via Disentangled Speaker and Accent Representations
• Accent Vector: Controllable Accent Manipulation for Multilingual TTS Without Accented Data
• CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models

Related papers

• Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
• Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
• Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems
• AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
• SoundWeaver: Compositional Warm-Starting for Text-to-Audio Diffusion Serving
• WASIL: In-the-Wild Arabic Spoken Interactions with LLMs