AISHELL-1

Overview edit

Variants: AISHELL-1

Associated Benchmarks

This dataset is used in 1 benchmark:

• Speech Recognition - Metrics: Word Error Rate (WER), Params(M)

Recent Benchmark Submissions

Research Papers

Recent papers with results on this dataset:

• FireRedASR: Open-Source Industrial-Grade Mandarin Speech Recognition Models from Encoder-Decoder to LLM Integration (2025) -
• CR-CTC: Consistency regularization on CTC for improved speech recognition (2024) -
• Lightweight Transducer Based on Frame-Level Criterion (2024) -
• Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition (2024) -
• Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models (2023) -
• Unimodal Aggregation for CTC-based Speech Recognition (2023) -
• BAT: Boundary aware transducer for memory-efficient and low-latency ASR (2023) -
• FunASR: A Fundamental End-to-End Speech Recognition Toolkit (2023) -
• Beyond Universal Transformer: block reusing with adaptor in Transformer for automatic speech recognition (2023) -
• Knowledge Transfer from Pre-trained Language Models to Cif-based Speech Recognizers via Hierarchical Distillation (2023) -
• MMSpeech: Multi-modal Multi-task Encoder-Decoder Pre-training for Speech Recognition (2022) -
• Improving Mandarin Speech Recogntion with Block-augmented Transformer (2022) -
• Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition (2020) -
• CAT: A CTC-CRF based ASR Toolkit Bridging the Hybrid and the End-to-end Approaches towards Data Efficiency and Low Latency (2020) -
• A Comparative Study on Transformer vs RNN in Speech Applications (2019) -
• End-to-end Speech Recognition with Adaptive Computation Steps (2018) -