#AI & Machine Learning

Policy-Adaptive Estimator Selection for Off-Policy Evaluation

Fine-grained Image Editing by Pixel-wise Guidance Using Diffusion Models

Rawgment: Noise-Accounted RAW Augmentation Enables Recognition in a Wide Variety of Environments

Efficient Joint Detection and Multiple Object Tracking with Spatially Aware Transformer

説明可能なデータバイアス緩和

AutoTTS: End-to-End Text-to-Speech Synthesis through Differentiable Duration Modeling

Improving Self-Supervised Learning for Audio Representations by Feature Diversity and Decorrelation

Nonparallel Emotional Voice Conversion for unseen speaker-emotion pairs using dual domain adversarial network Virtual Domain Pairing

The Pipeline System of ASR and NLU with MLM-based Data Augmentation toward STOP Low-resource Challenge

E-Branchformer-Based E2E SLU Toward Stop on-Device Challenge

A Study on the Integration of Pipeline and E2E SLU systems for Spoken Semantic Parsing toward STOP Quality Challenge

Joint Modelling of Spoken Language Understanding Tasks with Integrated Dialog History

Streaming Joint Speech Recognition and Disfluency Detection

An Attention-based Approach to Hierarchical Multi-label Music Instrument Classification

DiffRoll: Diffusion-based Generative Music Transcription with Unsupervised Pretraining Capability

Hierarchical Diffusion Models for Singing Voice Neural Vocoder

Music Mixing Style Transfer: A Contrastive Learning Approach to Disentangle Audio Effects

Unsupervised Vocal Dereverberation with Diffusion-based Generative Models

CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled Videos

ComFact: A Benchmark for Linking Contextual Commonsense Knowledge

Regularizing Score-based Models with Score Fokker-Planck Equations