论文解读
Robust Spoofed Speech Detection via Temporal Pyramid Modeling
音频深度伪造检测 | 6.7/10
自监督学习
论文解读
Spectro-Temporal Interference Confounds Phase Encoding in Spatial Audio Foundation Models
自监督学习 | 7.4/10
论文解读
From Self-Supervised Speech Models to Mixture-of-Experts for Robust Anti-Spoofing
自监督学习 | 7.5/10
论文解读
Mask, Sample, Revise: A Revisable CTMC Inference Stack for Guided Discrete Flow Matching Text-to-Speech
语音合成 | 6.8/10
论文解读
OmniVideo-100K: A Dataset for Audio-Visual Reasoning through Structured Scripts and Evidence Chains
数据增强 | 8.2/10
论文解读
Unsupervised Approaches for Global Prosodic Embedding Extraction
语音合成 | 7.8/10
论文解读
Decoding Insect Song: A Multitask Semisupervised Orthoptera Bioacoustic Classifier
音频分类 | 8.7/10
论文解读
Dolph2Vec: Self-Supervised Representations of Dolphin Vocalizations
音频分类 | 7.2/10
论文解读
From Tokens to Faces: Investigating Discrete Speech Representations for 3D Facial Animation
语音合成 | 7.9/10
论文解读
Leveraging Audio-LLMs to Filter Speech-to-Speech Training Data
语音翻译 | 8.4/10
论文解读
Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment
语音合成 | 9.7/10
论文解读
Context-Aware Multimodal Claim Verification in Spoken Dialogues
多模态模型 | 7.1/10
论文解读
Gumbel-BEARD: Automatic Layer Selection for Self-Supervised Adaptation of Whisper in Low-Resource Domains
语音识别 | 9.1/10
论文解读
Interpreting and Steering a Text-to-Speech Language Model with Sparse Autoencoders
语音合成 | 7.7/10
论文解读
Pretrained self-supervised speech models can recognize unseen consonants
语音识别 | 6.5/10
论文解读
SARA: A Dual-Stream VAE for High-Fidelity Speech Generation via Integrating Semantic and Acoustic Representations
语音合成 | 7.9/10
论文解读
UR-BERT: Scaling Text Encoders for Massively Multilingual TTS Through Universal Romanization and Speech Token Prediction
语音合成 | 8.1/10
论文解读
Automated Pronunciation Evaluation for Korean Toddler Speech using Speech Diarization and Self-Supervised Learning
说话人日志 | 6/10
论文解读
Multilingual Word-Level Forced Alignment with Self-Supervised Representations and Learned Dynamic Programming
自监督学习 | 6.3/10
论文解读
Overview of ESDD2: Environment-Aware Speech and Sound Deepfake Detection Challenge
数据增强 | 6.3/10