论文解读
Never Stop Speaking: a Denial-of-Service Attack on End-to-End Speech Language Models
语音交互 | 5.4/10
对抗训练
论文解读
From Inaudible Inputs to Model Failures: Low-Frequency Safety Risks in LALMs
音频理解 | 7.4/10
论文解读
AnyBand: Unified Multi-Bandwidth Speech Extension via Frequency-Aware In-Context Spectral Infilling
语音超分 | 5.9/10
论文解读
Teffic-Audio: Tell Fact from Fiction
语音伪造检测 | 6.8/10
论文解读
Leveraging Gradient Reversal Loss and Multitask Learning for Datasets-Aware Audio Deepfake Detection
语音伪造检测 | 7.3/10
论文解读
Multimodal Domain Generalization for Depression Detection: An Attention-Based BiLSTM Network with Domain-Adversarial Training
音频分类 | 6.4/10
论文解读
HARP: Harmonic-Aware Residual Partitioning for Neural Audio Codecs
音频编码 | 9.6/10
论文解读
Multi-Level Privacy-Preserving Dementia Detection from Speech via Targeted Adversarial Obfuscation and Representation Learning
语音属性识别 | 5.5/10
论文解读
Natural Backdoor Attacks on Speech Recognition Models
语音识别 | 3.5/10
论文解读
SpeechGuard: Online Defense against Backdoor Attacks on Speech Recognition Models
语音识别 | 6.0/10
每日研究速递
语音/音乐/音频论文速递 2026-07-20
共分析 15 篇语音/AI 论文
论文解读
Cross Domain Few-Shot Class-Incremental Audio Classification Via Adversarial Contrastive Learning
音频分类 | 7.4/10
论文解读
Learning Robust Pair Confidence for Multimodal Emotion-Cause Pair Extraction
多模态模型 | 7.5/10
每日研究速递
语音/音乐/音频论文速递 2026-06-18
共分析 36 篇语音/AI 论文
论文解读
ROMPAR: Morphological Completion and Demographic Unlearning for Romanian-Accented Speech Recognition
语音识别 | 6.2/10
论文解读
Speaker-Invariant Representation Learning for Spoofing Detection via Gradient Reversal and A Variational Information Bottleneck
对抗训练 | 7.1/10
论文解读
LiveBand: Live Accompaniment Generation in the Audio Domain
音乐生成 | 8/10
每日研究速递
语音/音乐/音频论文速递 2026-06-03
共分析 40 篇语音/AI 论文
论文解读
Generative Adversarial Post-Training Mitigates Reward Hacking in Live Human-AI Music Interaction
音乐生成 | 7.0/10
论文解读
Dual-LoRA: Parameter-Efficient Adversarial Disentanglement for Cross-Lingual Speaker Verification
说话人验证 | 7.5/10