%Aigaion2 BibTeX export from Idiap Publications
%Monday 14 July 2025 04:26:39 PM

@INPROCEEDINGS{Rangappa_INTERSPEECH_2025,
                      author = {Rangappa, Pradeep and Carofilis, Andr{\'{e}}s and Prakash, Jeena and Kumar, Shashi and Burdisso, Sergio and Madikeri, Srikanth and Villatoro-Tello, Esa{\'{u}} and Sharma, Bidisha and Motlicek, Petr and Hacioğlu, Kadri and Venkatesan, Shankar and Vyas, Saurabh and Stolcke, Andreas},
                    keywords = {Data Selection, speech recognition, whisper, Zipformer},
                    projects = {UNIPHORE, ELOQUENCE},
                       title = {Efficient Data Selection for Domain Adaptation of ASR Using Pseudo-Labels and Multi-Stage Filtering},
                   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.},
                         pdf = {https://publications.idiap.ch/attachments/papers/2025/Rangappa_INTERSPEECH_2025.pdf}
}