2026-03-15T17:06:32Z https://ipsj.ixsq.nii.ac.jp/oai

oai:ipsj.ixsq.nii.ac.jp:00231311 2025-01-19T10:48:53Z 1164:5159:11151:11431

Investigation of Adapter for Automatic Speech Recognition in Noisy Environment Investigation of Adapter for Automatic Speech Recognition in Noisy Environment Hao, Shi Tatsuya, Kawahara Hao, Shi Tatsuya, Kawahara 分野横断（2） Adapting an automatic speech recognition (ASR) system to unseen noise environments is crucial. Integrating adapters into neural networks has emerged as a potent technique for transfer learning. This study thoroughly investigates adapter-based ASR adaptation in noisy environments. We conducted experiments using the CHiME-4 dataset. The results show that inserting the adapter in the shallow layer yields superior effectiveness, and there is no significant difference between adapting solely within the shallow layer and adapting across all layers. The simulated data helps the system to improve its performance under real noise conditions. Nonetheless, when the amount of data is the same, the real data is more effective than the simulated data. Multi-condition training is still useful for adapter training. Furthermore, integrating adapters into speech enhancement-based ASR systems yields substantial improvements. Adapting an automatic speech recognition (ASR) system to unseen noise environments is crucial. Integrating adapters into neural networks has emerged as a potent technique for transfer learning. This study thoroughly investigates adapter-based ASR adaptation in noisy environments. We conducted experiments using the CHiME-4 dataset. The results show that inserting the adapter in the shallow layer yields superior effectiveness, and there is no significant difference between adapting solely within the shallow layer and adapting across all layers. The simulated data helps the system to improve its performance under real noise conditions. Nonetheless, when the amount of data is the same, the real data is more effective than the simulated data. Multi-condition training is still useful for adapter training. Furthermore, integrating adapters into speech enhancement-based ASR systems yields substantial improvements. 情報処理学会 2023-11-25 eng technical report https://ipsj.ixsq.nii.ac.jp/records/231311 2188-8663 AN10442647 研究報告音声言語情報処理（SLP） 2023-SLP-149 19 1 6 https://ipsj.ixsq.nii.ac.jp/record/231311/files/IPSJ-SLP23149019.pdf application/pdf 206.7 kB 2025-11-25