Shinji Watanabe

UALM: Unified Audio Language Model for Understanding, Generation and Reasoning

MAPSS: Manifold-based Assessment of Perceptual Source Separation

BLAB: Brutally Long Audio Bench

Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage

CartoonSing: Unifying Human and Nonhuman Timbres in Singing Generation

Speech-DRAME: A Framework for Human-Aligned Benchmarks in Speech Role-Play

ARECHO: Autoregressive Evaluation via Chain-Based Hypothesis Optimization for Speech Multi-Metric Estimation

Context-aware Dynamic Pruning for Speech Foundation Models

Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks

Talking Turns: Benchmarking Audio Foundation Models on Turn-Taking Dynamics

OWLS: Scaling Laws for Multilingual Speech Recognition and Translation Models

Unifying Diarization, Separation, and ASR with Multi-Speaker Encoder

Speaking Guided by Listening: Unsupervised Text-to-Speech Generative Model Guided by End-to-End Speech Recognition