论文解读
Video = World + Event Stream
音频理解 | 4.9/10
自监督学习
论文解读
Rethinking Speech Foundation Model Fine-tuning: Better SFT or Better Match?
语音情感识别 | 6.7/10
论文解读
Self-supervised Speech Comparison for L2 Phone, Rhythm, and Intonation Scoring
音频理解 | 7.7/10
论文解读
AutoSIFT: Automatic Style Sifting for Controllable Speech Generation with Arbitrary Style Infilling
语音合成 | 6.5/10
论文解读
Investigating the Integration of Spatial Information in Foundation-Model-Based Speaker Diarization
说话人日志 | 6.6/10
论文解读
PolarBM: Complex-valued Boltzmann Machine for Modeling Audio Signals in Polar and Log-polar Coordinates
语音增强 | 5.8/10
论文解读
ARIMA: Reconstruction-Grounded Predictive Representation Learning for Symbolic Music
自监督学习 | 7.7/10
论文解读
BeatEdit: Symbolic Music Generation as Explicit Editing
音乐生成 | 8.9/10
论文解读
Casting Everything to Online API Services? A Survey of Integrating Localized Speech Recognition Models in Robotic Systems
语音识别 | 5.4/10
论文解读
Dance to Music Generation leveraging Pre-training with Unpaired data and Contrastive Alignment
音乐生成 | 7.5/10
论文解读
Data Augmentation for L2 English Speaking Assessment using TTS
语音质量评估 | 7.0/10
论文解读
ECHOv2: Two-Level Band-Splitting Representation Learning for Anomalous Sound Detection
音频事件检测 | 8.2/10
论文解读
Evaluating SSL and ViViT Architectures for Cross-Corpus Audio MOS Prediction via LODO Validation
语音质量评估 | 8.3/10
论文解读
Evidence Subspace Projection: Measuring How Much Evidence Explains Deepfake Detection in Self-Supervised Speech Models
语音伪造检测 | 8.1/10
论文解读
GigaAM Multilingual: Foundation Model for Underrepresented Languages
语音识别 | 8.1/10
论文解读
Learn2Chat: Rethinking Dyadic Talking Heads via Interaction-Modulated Monologic Priors
音视频生成 | 6.8/10
论文解读
Listen to the Features: Voice Anonymization Driven by Content Embedding Matching over Signal Reconstruction
语音克隆 | 6.5/10
论文解读
Local Multimodal Music Alignment from Global Supervision
对比学习 | 7.6/10
论文解读
MeloBottleneck: Self-Supervised Melody Skeleton Extraction with a Latent Subsequence Bottleneck
音乐理解 | 7.5/10
论文解读
Synchronized Three-Dimensional Vocal-Tract Motion for Speech Synchronization via Joint-Embedding Predictive Architecture Alignment
语音合成 | 5.7/10