CSJ

Corpus of Spontaneous Japanese, or CSJ, is a large-scale database of spontaneous Japanese. It contains speech signal and transcription of about 7 million words along with various annotations like POS and phonetic labels. After describing its design issues, preliminary evaluation of the CSJ was presented. The results su

Papers using CSJ (8)

Retrieval-Augmented Speech Recognition Approach for Domain Challenges2025 · 4 citesSpiralformer: Low Latency Encoder for Streaming Speech Recognition with Circular Layer Skipping and Early Exiting2025Whale: Large-Scale multilingual ASR model with w2v-BERT and E-Branchformer with large speech data2025Structured State Space Decoder for Speech Recognition and Synthesis2022 · 1 citesA Lexical-aware Non-autoregressive Transformer-based ASR Model2023Benchmarking Japanese Speech Recognition on ASR-LLM Setups with Multi-Pass Augmented Generative Error Correction2024Joint Optimization of Streaming and Non-Streaming Automatic Speech Recognition with Multi-Decoder and Knowledge Distillation2024Efficient and Robust Long-Form Speech Recognition with Hybrid H3-Conformer2024