AISHELL-4

AISHELL-4 is a dataset used to evaluate speaker diarization and recognition performance in large audio-language models.

Papers using AISHELL-4 (6)

Speaker-Reasoner: Scaling Interaction Turns and Reasoning Patterns for Timestamped Speaker-Attributed ASR2026Joint Learning Global-Local Speaker Classification to Enhance End-to-End Speaker Diarization and Recognition2026Lightweight and Robust Multi-Channel End-to-End Speech Recognition with Spherical Harmonic Transform2025Asobo: Attentive Beamformer Selection For Distant Speaker Diarization In Meetings2024Token-level Speaker Change Detection Using Speaker Difference and Speech Content via Continuous Integrate-and-fire2022ASoBO: Attentive Beamformer Selection for Distant Speaker Diarization in Meetings2024