论文解读
StylePitcher: Generating Style-Following and Expressive Pitch Curves for Versatile Singing Tasks
歌唱语音合成 | 7.5/10
流匹配
论文解读
Symphony Rendering: Midi and Composer-Conditioned Auto Orchestration with Flow-Matching Transformers
音乐生成 | 7.0/10
论文解读
Task Vector in TTS: Toward Emotionally Expressive Dialectal Speech Synthesis
语音合成 | 7.0/10
论文解读
TMD-TTS: A Unified Tibetan Multi-Dialect Text-to-Speech Framework for Ü-Tsang, Amdo and Kham Speech Dataset Generation
语音合成 | 7.5/10
论文解读
Towards Real-Time Generative Speech Restoration with Flow-Matching
语音增强 | 6.0/10
论文解读
Training Flow Matching Models with Reliable Labels via Self-Purification
语音合成 | 7.5/10
论文解读
Universr: Unified and Versatile Audio Super-Resolution Via Vocoder-Free Flow Matching
音频超分辨率 | 8.0/10
论文解读
V2A-DPO: Omni-Preference Optimization for Video-To-Audio Generation
视频到音频生成 | 7.5/10
论文解读
VoxMorph: Scalable Zero-Shot Voice Identity Morphing via Disentangled Embeddings
语音克隆 | 9.0/10
论文解读
MAGIC-TTS: Fine-Grained Controllable Speech Synthesis with Explicit Local Duration and Pause Control
语音合成 | 7.0/10
论文解读
Speech Enhancement Based on Drifting Models
语音增强 | 7.5/10
论文解读
Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling
语音合成 | 7.5/10
论文解读
UniSonate: A Unified Model for Speech, Music, and Sound Effect Generation with Text Instructions
音频生成 | 8.5/10
论文解读
MAGIC-TTS: Fine-Grained Controllable Speech Synthesis with Explicit Local Duration and Pause Control
语音合成 | 7.5/10
每日研究速递
语音/音乐/音频论文速递 2026-04-25
共分析 2 篇语音/AI 论文
论文解读
ATRIE: Adaptive Tuning for Robust Inference and Emotion in Persona-Driven Speech Synthesis
语音合成 | 7.0/10
论文解读
MAGIC-TTS: Fine-Grained Controllable Speech Synthesis with Explicit Local Duration and Pause Control
语音合成 | 7.5/10
论文解读
X-VC: Zero-shot Streaming Voice Conversion in Codec Space
1. **问题**：零样本语音转换需要同时实现高质量的说话人特征迁移和低延迟的流式推理，这是一个尚未很好解决的挑战。 2. **方法核心**：提出X-VC系统，在预训练的SAC语音编解码器的潜在空间中进行一步转换。核心是一个双条件声学转换器，它联合处理源语音的编解码器潜在表示和目标参考语音的帧级梅尔
论文解读
ATRIE: Adaptive Tuning for Robust Inference and Emotion in Persona-Driven Speech Synthesis
本文针对现有语音合成系统在生成角色驱动、情感丰富的语音时难以同时保持角色身份一致性和情感表达准确性的问题，提出了ATRIE框架。其核心是**Persona-Prosody Dual-Track (P2-DT) 架构**，将语音生成解耦为静态的**音色轨道**（通过标量量化保持身份锚点）和动态的**韵
论文解读
Anonymization, Not Elimination: Utility-Preserved Speech Anonymization
这篇论文针对语音数据隐私保护中“隐私泄露”与“数据效用损失”的核心矛盾，提出了一个新颖的两阶段框架。首先，为解决语音匿名化（保护“谁在说”）中身份多样性不足和可控性差的问题，提出了基于流匹配的说话人嵌入匿名器（F3-VA），它能生成多样且与原始说话人充分分离的新身份。其次，为解决内容匿名化（保护“说