论文解读
SpeakerCard-1M: An Evidence-Grounded Speaker Card Corpus for In-the-Wild Speaker Verification
说话人验证 | 7.4/10
预训练
论文解读
MOSS-Audio Technical Report
语音识别 | 9.2/10
论文解读
SN-WER: Script-Normalized WER for Multi-Script Indic ASR Evaluation
语音识别 | 5.3/10
论文解读
Improving acoustic drone detection generalization through pretraining and data augmentation
音频事件检测 | 7.7/10
论文解读
Beyond Binary: Speech Representations Across the Cognitive Score Hierarchy
自监督学习 | 8.1/10
论文解读
FalAR: A Large-scale Speaker-Annotated European Portuguese Speech Corpus of Parliamentary Sessions
语音识别 | 5.5/10
论文解读
Frame-Aligned Fusion of Canary and WavLM for Non-Intrusive Intelligibility Prediction of Hearing-Aid-Processed Speech
语音质量评估 | 10/10
论文解读
Speech Quality Embeddings for Improved Detection and Classification of Degradations in Speech Signals
语音质量评估 | 5.8/10
论文解读
SemaVoice: Semantic-Aware Continuous Autoregressive Speech Synthesis
语音合成 | 6.8/10
论文解读
Beyond Content: A Comprehensive Speech Toxicity Dataset and Detection Framework Incorporating Paralinguistic Cues
音频分类 | 6.5/10
论文解读
AudioMosaic: Contrastive Masked Audio Representation Learning
音频分类 | 7.3/10
论文解读
FSD50K-Solo: Automated Curation of Single-Source Sound Events
数据清洗 | 5.5/10
论文解读
Masked Autoencoders with Limited Data: Does It Work? A Fine-Grained Bioacoustics Case Study
音频分类 | 5.5/10
论文解读
Text-Dependent Speaker Verification (TdSV) Challenge 2024: Team Naive System Report
说话人验证 | 5.5/10
论文解读
Bypassing Direct Reconstruction: Speech Detection from MEG via Large-Scale Audio Retrieval
语音活动检测 | 7.0/10
论文解读
CORTEG: Foundation Models Enable Cross-Modality Representation Transfer from Scalp to Intracranial Brain Recordings
脑机接口 | 6.5/10
论文解读
Voice Biomarkers for Depression and Anxiety
语音生物标志物 | 1.0/10
论文解读
Anisotropic Modality Align
Anisotropic Modality Align
论文解读
BeeVe: Unsupervised Acoustic State Discovery in Honey Bee Buzzing
BeeVe: Unsupervised Acoustic State Discovery in Honey Bee Buzzing
论文解读
Sparse Autoencoders as Plug-and-Play Firewalls for Adversarial Attack Detection in VLMs
Sparse Autoencoders as Plug-and-Play Firewalls for Adversarial Attack Detection in VLMs