论文解读
FC-TTS: Style and Timbre Control in Zero-Shot Text-to-Speech with Disentangled Speech Representations
语音合成 | 8.4/10
论文速递
论文解读
Hidden in Plain Tokens: Simply Robust, Gradient-Free Watermark for Synthetic Audio
音频水印 | 6.2/10
论文解读
Multilingual Phonological Feature Recognition with Self-Supervised Speech Models
语音识别 | 7.7/10
论文解读
Music Transcription with (Almost) No Supervision
音乐转录 | 10/10
论文解读
Proactive for Uncertainty: Cause-Aware Error Diagnosis and Interactive Clarification for Spoken Dialogue Systems
语音识别 | 9.6/10
论文解读
Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems
语音识别 | 6.0/10
论文解读
Rubato: Transcribing Piano Music with Timestamps
音乐转录 | 7.5/10
论文解读
Score-Agnostic Structure Analysis in Large-Scale Performance Datasets
音乐信息检索 | 4.1/10
论文解读
SpongeBob: Sync-Aware Harmonious Audio-Visual Generative Editing
语音编辑 | 8.6/10
论文解读
StrTransformer: Source-Wise Structured Transformers for Unsupervised Blind Source Recovery
StrTransformer: Source-Wise Structured Transformers for Unsupervised Blind Source Recovery
论文解读
Subspace Track-before-Detect for Passive Multi-Target Tracking with Unknown Emitted Signals
声源定位 | 5.5/10
论文解读
Test-Time Self-Adaptive Conditioning for Stable Audio-Driven Talking-Head Generation
Test-Time Self-Adaptive Conditioning for Stable Audio-Driven Talking-Head Generation
论文解读
Thaka at KSAA-2026 Task 2: Regularized Fine-Tuning for Arabic Speech Diacritization
语音增强 | 5.5/10
论文解读
The Symmetric Location Problem: a Song of Efficiency and Robustness
The Symmetric Location Problem: a Song of Efficiency and Robustness
论文解读
Time Segmented Beamforming via Dynamic Programming: Theory and Implementation
实时处理 | 7.7/10
论文解读
Toward Native Multimodal Modeling: A Roadmap
多模态模型 | 10/10
论文解读
Toward Natural Emotional Text-To-Speech System with Fine-Grained Non-Verbal Expression Control
语音合成 | 5.0/10
论文解读
Ultra-Low-Bitrate Mel-Spectrogram-based Neural Speech Coding with Flow-Matching-based Refinement and Vocoding-driven Reconstruction
语音编码 | 9.9/10
论文解读
WaveNeXt 2: ConvNeXt-Based Fast Neural Vocoders With Residual Denoising and Sub-Modeling for GAN and Diffusion Models
语音合成 | 9.4/10
论文解读
Zero-Shot Parkinson's Disease Detection from Speech: Comparing Large Audio and Language Models
大语言模型 | 5/10