论文解读
PashtoTTS-Bench: automated screening for low-resource non-Latin-script text-to-speech
语音合成 | 6.5/10
Posts
论文解读
PilotTTS: A Disciplined Modular Recipe for Competitive Speech Synthesis
语音合成 | 9.2/10
论文解读
PitchBench: Measuring Pitch Hearing in Audio-Language Models
基准测试 | 9.7/10
论文解读
Proactive for Uncertainty: Cause-Aware Error Diagnosis and Interactive Clarification for Spoken Dialogue Systems
语音识别 | 6.8/10
论文解读
Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems
语音识别 | 7.5/10
论文解读
Rubato: Transcribing Piano Music with Timestamps
音乐转录 | 10/10
论文解读
Score-Agnostic Structure Analysis in Large-Scale Performance Datasets
音乐信息检索 | 6.5/10
论文解读
Subspace Track-before-Detect for Passive Multi-Target Tracking with Unknown Emitted Signals
信号处理基础 | 6.4/10
论文解读
Test-Time Self-Adaptive Conditioning for Stable Audio-Driven Talking-Head Generation
语音合成 | 7.7/10
论文解读
Thaka at KSAA-2026 Task 2: Regularized Fine-Tuning for Arabic Speech Diacritization
语音识别 | 6.0/10
论文解读
Time Segmented Beamforming via Dynamic Programming: Theory and Implementation
自适应滤波 | 8/10
论文解读
Toward Natural Emotional Text-To-Speech System with Fine-Grained Non-Verbal Expression Control
语音合成 | 6.3/10
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 | 8.1/10
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 | 8.5/10
论文解读
Why Can't They Remember? Uncovering Representation and Retrieval Bottlenecks in Multi-Turn Acoustic Memory
语音识别 | 7/10
论文解读
Zero-Shot Parkinson's Disease Detection from Speech: Comparing Large Audio and Language Models
大语言模型 | 5.2/10
每日研究速递
语音/音乐/音频论文速递 2026-05-27
共分析 39 篇语音/AI 论文
论文解读
A Multimodal Framework for Dementia Detection via Linguistic and Acoustic Representation Learning
语音情感识别 | 7/10
论文解读
AVBench: Human-Aligned and Automated Evaluation Benchmark for Audio-Video Generative Models
音频生成 | 7/10
论文解读
Continual Speaker Identity Unlearning with Minimal Interference
语音合成 | 8.6/10