Benchmarking Japanese Speech Recognition on ASR-LLM Setups with Multi-Pass Augmented Generative Error Correction
It addresses ASR errors for Japanese language processing, presenting the first GER benchmark for Japanese, but is incremental as it builds on existing LLM-based GER methods.
This work tackled the problem of improving Japanese automatic speech recognition (ASR) by introducing a multi-pass augmented generative error correction (MPA GER) method using large language models (LLMs), resulting in performance improvements on SPREDS-U1-ja and CSJ datasets with benchmarks on 0.9-2.6k text utterances.
With the strong representational power of large language models (LLMs), generative error correction (GER) for automatic speech recognition (ASR) aims to provide semantic and phonetic refinements to address ASR errors. This work explores how LLM-based GER can enhance and expand the capabilities of Japanese language processing, presenting the first GER benchmark for Japanese ASR with 0.9-2.6k text utterances. We also introduce a new multi-pass augmented generative error correction (MPA GER) by integrating multiple system hypotheses on the input side with corrections from multiple LLMs on the output side and then merging them. To the best of our knowledge, this is the first investigation of the use of LLMs for Japanese GER, which involves second-pass language modeling on the output transcriptions generated by the ASR system (e.g., N-best hypotheses). Our experiments demonstrated performance improvement in the proposed methods of ASR quality and generalization both in SPREDS-U1-ja and CSJ data.