论文解读
The Watermark Shortcut: How Provenance Marking Sabotages Audio Deepfake Detection
数据增强 | 6.8/10
数据增强
论文解读
FlowEdit: Associative Memory for Lifelong Pronunciation Adaptation in Flow-Matching TTS
语音合成 | 10/10
论文解读
Improving Code-Switching ASR with Code-Mixing Guided Synthetic Speech
语音识别 | 7.6/10
论文解读
Improving End-to-End Speech Recognition for Dysarthric Speech through In-Domain Data Augmentation
语音识别 | 6.5/10
论文解读
Investigating Human-Model Discrepancies in Speech Quality Assessment via Acoustic and Prosodic Perturbations
语音合成 | 6.9/10
论文解读
Leveraging systems' non-linearity to tackle the scarcity of data in the design of Intelligent Fault Diagnosis Systems
数据增强 | 5.5/10
论文解读
Low-Burden Data Augmentation for Dysarthric ASR via Zero-Shot Voice Cloning
语音识别 | 8.7/10
论文解读
MixProLAP: Mixture-Induced Uncertainty Modeling for Probabilistic Language-Audio Pretraining
音频检索 | 5.7/10
论文解读
S-JEPA : Soft Clustering Anchors for Self-Supervised Speech Representation Learning
语音识别 | 8.7/10
论文解读
Segment-Level Mandarin Chinese Speech-Based Cognitive Impairment Detection via an Autoencoder with Contrastive Learning
对比学习 | 6.5/10
论文解读
Augmenting Dysarthric Speech Severity Assessment with MOS Supervision
语音质量评估 | 7/10
论文解读
DASH: Dual-View Self-Distillation with Multi-Layer Hidden Representations for Robust Speech Recognition
语音识别 | 6.6/10
论文解读
Low-resource Language Discrimination Towards Chinese Dialects with Transfer learning and Data Augmentation
语音识别 | 5.5/10
论文解读
An Analysis of the Effectiveness of Synthetic Speech Data for ASR Fine-tuning in Selected Indic Languages
语音识别 | 5.7/10
论文解读
Descriptor: Certus Caliber Classification Gunshot Dataset (C3GD)
音频分类 | 5.9/10
论文解读
DeSRPA: Decoupled Speech Role-Playing Agent via Inference-Time Intervention
语音合成 | 7.3/10
论文解读
Improving low-resource ASR using bilingual fine-tuning with language identification: a cross-linguistic evaluation
语音识别 | 7.5/10
论文解读
Learning task-specific subspaces via interventional post-training of speech foundation models
自监督学习 | 6.2/10
论文解读
Turning music identification into a neural forward pass
音频分类 | 7.4/10
论文解读
An Empirical Study on Learning Latent Representations for Emotional Speech Synthesis
语音合成 | 8.2/10