Efficient Data Selection for Domain Adaptation of ASR Using Pseudo-Labels and Multi-Stage Filtering
| Type of publication: | Conference paper |
| Citation: | Rangappa_INTERSPEECH_2025 |
| Booktitle: | Proc. Interspeech |
| Year: | 2025 |
| Abstract: | Fine-tuning pretrained ASR models for specific domains is challenging for small organizations with limited labeled data and computational resources. Here we explore different data selection pipelines and propose a robust approach that improves ASR adaptation by filtering pseudo-labels generated using Whisper (encoder-decoder) and Zipformer (transducer) models. Our approach integrates multiple selection strategies---including word error rate (WER) prediction, named entity recognition (NER), and character error rate (CER) analysis---to extract high-quality training segments. We evaluate our method on Whisper and Zipformer using a 7500-hour baseline, comparing it to a CER-based approach relying on hypotheses from three ASR systems. Fine-tuning on 7500 hours of pseudo-labeled call center data achieves 12.3% WER, while our filtering reduces the dataset to 100 hours (1.4%) with similar performance; a similar trend is observed on Fisher English. |
| Keywords: | Data Selection, speech recognition, whisper, Zipformer |
| Projects: |
UNIPHORE ELOQUENCE |
| Authors: | |
| Added by: | [UNK] |
| Total mark: | 0 |
|
Attachments
|
|
|
|
|
Notes
|
|
|
|
|
