论文解读
RABBiT: Rapidly adaptive BOLD foundation model via brain-tuning for accurate zero-shot and few-shot prediction of speech-elicited responses in the brain
音频理解 | 8.1/10
自监督学习
论文解读
Speaker-Disentangled Chunk-Wise Regression for Syllabic Tokenization
语音编码 | 7.9/10
论文解读
Towards Language-Agnostic Speech Inversion
语音属性识别 | 5.6/10
论文解读
Alethia: a Foundational Encoder for Voice Deepfakes
语音伪造检测 | 7.6/10
论文解读
BAT: Better Audio Transformer Guided by Convex Gated Probing
音频分类 | 8.6/10
论文解读
Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models
语音合成 | 8/10
论文解读
HyperPotter: Spell the Charm of High-Order Interactions in Audio Deepfake Detection
音频伪造检测 | 7.9/10
论文解读
NeuroCLUS: A Foundation Model with Functional Clustering for Intracranial Neural Decoding
语音识别 | 6/10
论文解读
OmniVideo-R1: Reinforcing Audio-visual Reasoning with Query Intention and Modality Attention
音视频问答 | 7.5/10
论文解读
Pianist Transformer: Towards Expressive Piano Performance Rendering via Scalable Self-Supervised Pre-Training
音乐生成 | 8.1/10
论文解读
Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis
音视频生成 | 7.2/10
论文解读
SURF: Separation via Unsupervised Remixing Flow
语音分离 | 6.2/10
论文解读
VocSim A Training-free Benchmark for Zero-shot Content Identity in Single-source Audio
音频检索 | 8.2/10
论文解读
LMPAN: A Lightweight Multi-Path Alignment Network for Joint Full-Duplex Acoustic Echo Cancellation and Noise Suppression
语音增强 | 6.2/10
论文解读
Pmeta-TLA: Backdoor Attacks for Speech Classification Models via Meta-Learning with Timbre Leakage Attack
语音唤醒 | 6/10
论文解读
SPARCLE: SPeaker-aware Aligned Representations via Contrastive Language Embeddings
语音合成 | 5.8/10
论文解读
TurnNat: Automatic Evaluation of Turn-Taking Naturalness in Dyadic Spoken Dialogue
语音交互 | 7/10
论文解读
AV-SyncBench: Decoupled Benchmarking of Temporal and Semantic Audio-Visual Synchronization
音视频理解 | 8.5/10
论文解读
Disentangling Speaker and Language Effects in Cross-Lingual Speaker Verification for Iberian Languages
说话人验证 | 5.6/10
论文解读
BEST-RQ-2: Contextualize-Then-Predict, a Two-Step Approach for Self-Supervised Audio Representations
语音识别 | 6.9/10