#AI & Machine Learning

キャラクター対話AI技術

Residual Language Model for End-to-end Speech Recognition

Distributed and Adaptive Edge-based AI Models for Sensor Networks (DAISeN)

Towards Developing a Multi-Modal Video Recommendation System

SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization

M2FNet: Multi-Modal Fusion Network for Emotion Recognition in Conversation

Bootstrapped Representation Learning for Skeleton-Based Action Recognition

Degree-of-linear-polarization-based Color Constancy

An Inductive System Monitoring Approach for GNSS Activation

レザバー計算による組込み指向型音声分類システム

Spatial mixup: Directional loudness modification as data augmentation for sound event localization and detection

Improving Character Error Rate Is Not Equal to Having Clean Speech: Speech Enhancement for ASR Systems with Black-box Acoustic Models

Good Examples Make A Faster Learner: Simple Demonstration-based Learning for Low-resource NER

Automatic DJ Transitions with Differentiable Audio Effects and Generative Adversarial Networks

Amicable Examples for Informed Source Separation

Spatial Data Augmentation with Simulated Room Impulse Responses for Sound Event Localization and Detection

Source Mixing and Separation Robust Audio Steganography

Run-and-Back Stitch Search: Novel Block Synchronous Decoding For Streaming Encoder-Decoder ASR

Polyphone Disambiguation and Accent Prediction Using Pre-Trained Language Models in Japanese TTS Front-End

NVC-Net: End-to-End Adversarial Voice Conversion

Music Source Separation with Deep Equilibrium Models