论文解读
Continuous-Token Diffusion for Speaker-Referenced TTS in Multimodal LLMs
语音合成 | 8.0/10
语音合成
子标签
下方只统计已核验方向的论文记录，按已核身份去重，身份待核时按页面保留。“直接”只含明确标注该方向的论文；“含子树”同时包含下级方向。点击名称进入论文库继续筛选；数量与上方按标签名称收录的页面数不同。
论文解读
CosyAccent: Duration-Controllable Accent Normalization using Source-Synthesis Training Data
语音转换 | 7.8/10
论文解读
Cross-Lingual F5-TTS: Towards Language-Agnostic Voice Cloning and Speech Synthesis
语音克隆 | 7.5/10
论文解读
DAIEN-TTS: Disentangled Audio Infilling for Environment-Aware Text-to-Speech Synthesis
语音合成 | 8.0/10
论文解读
Deep Dubbing: End-to-End Auto-Audiobook System with Text-to-Timbre and Context-Aware Instruct-TTS
语音合成 | 7.5/10
论文解读
Direct Preference Optimization For Speech Autoregressive Diffusion Models
语音合成 | 7.5/10
论文解读
Discrete Diffusion for Generative Modeling of Text-Aligned Speech Tokens
语音合成 | 7.5/10
论文解读
DMP-TTS: Disentangled Multi-Modal Prompting for Controllable Text-to-Speech with Chained Guidance
语音合成 | 7.5/10
论文解读
Do You Hear What I Mean? Quantifying the Instruction-Perception GAP in Instruction-Guided Expressive Text-to-Speech Systems
语音合成 | 8.0/10
论文解读
ECSA: Dual-Branch Emotion Compensation for Emotion-Consistent Speaker Anonymization
语音匿名化 | 8.5/10
论文解读
EMG-to-Speech with Fewer Channels
语音合成 | 7.5/10
论文解读
Emilia-NV: A Non-Verbal Speech Dataset with Word-Level Annotation for Human-Like Speech Modeling
语音识别 | 7.5/10
论文解读
EMORL-TTS: Reinforcement Learning for Fine-Grained Emotion Control in LLM-based TTS
语音合成 | 8.5/10
论文解读
EmoShift: Lightweight Activation Steering for Enhanced Emotion-Aware Speech Synthesis
语音合成 | 7.0/10
论文解读
Emotion-Aligned Generation in Diffusion Text to Speech Models Via Preference-Guided Optimization
语音合成 | 8.0/10
论文解读
Emotional Damage: Investigating Safety Vulnerabilities of Large Audio-Language Models Under Speaker Emotional Variations
音频安全 | 7.5/10
论文解读
Emotional Dimension Control in Language Model-Based Text-To-Speech: Spanning a Broad Spectrum of Human Emotions
语音合成 | 7.5/10
论文解读
Entropy-Guided GRVQ for Ultra-Low Bitrate Neural Speech Codec
语音合成 | 7.5/10
论文解读
Erasing Your Voice Before it’s Heard: Training-Free Speaker Unlearning for Zero-Shot Text-to-Speech
语音合成 | 7.5/10
论文解读
FED-PISA: Federated Voice Cloning Via Personalized Identity-Style Adaptation
语音克隆 | 8.0/10