论文解读
SpeechMapper: Speech-To-Text Embedding Projector for LLMs
语音大模型 | 7.0/10
零样本
论文解读
Spiking Attention Network: A Hybrid Neuromorphic Approach to Underwater Acoustic Localization and Zero-Shot Adaptation
声源定位 | 7.0/10
论文解读
Spiking Temporal-Enhanced Network for Zero-Shot Audio-Visual Learning
音频分类 | 7.0/10
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
论文解读
Synthesized Data Selection via Score Distribution Matching for Te Reo Māori Automatic Speech Recognition
语音识别 | 8.0/10
论文解读
T-Cache: Fast Inference For Masked Generative Transformer-Based TTS Via Prompt-Aware Feature Caching
语音合成 | 9.0/10
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
TASU: Text-only Alignment for Speech Understanding
语音识别 | 7.0/10
论文解读
Thinking While Listening: Simple Test Time Scaling for Audio Classification
音频分类 | 6.5/10
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
VoXtream: Full-Stream Text-To-Speech With Extremely Low Latency
语音合成 | 8.5/10
论文解读
WavLink: Compact Audio–Text Embeddings with a Global Whisper Token
音频检索 | 8.0/10
论文解读
Why Do Speech Language Models Fail to Generate Semantically Coherent Outputs? A Modality Evolving Perspective
语音生成 | 7.0/10
论文解读
ZSV2C-MLLM: Zero-Shot Visual Voice Cloning Via Multimodal Large Language Models
语音克隆 | 6.5/10
论文解读
MAGIC-TTS: Fine-Grained Controllable Speech Synthesis with Explicit Local Duration and Pause Control
语音合成 | 7.0/10
论文解读
Beyond Acoustic Sparsity and Linguistic Bias: A Prompt-Free Paradigm for Mispronunciation Detection and Diagnosis
发音错误检测 | 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
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