@inproceedings{5359d163a7c840a68910d3311a4a212b,
title = "Utilizing WAV2VEC in database-independent voice disorder detection",
abstract = "Automatic detection of voice disorders from acoustic speech signals can help to improve reliability of medical diagnosis. However, the real-life environment in which speech signals are recorded for diagnosis can be different from the environment in which the detection system{\textquoteright}s training data was originally collected. This mismatch between the recording conditions can decrease detection performance in practical scenarios. In this work, we propose to use a pre-trained wav2vec 2.0 model as a feature extractor to build automatic detection systems for voice disorders. The embeddings from the first layers of the context network contain information about phones, and these features are useful in voice disorder detection. We evaluate the performance of the wav2vec features in single-database and crossdatabase scenarios to study their generalizability to unseen speakers and recording conditions. The results indicate that the wav2vec features generalize better than popular spectral and cepstral baseline features.",
author = "Saska Tirronen and Farhad Javanmardi and Manila Kodali and Sudarsana Kadiri and Paavo Alku",
year = "2023",
doi = "10.1109/ICASSP49357.2023.10094798",
language = "English",
series = "Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing",
publisher = "IEEE",
booktitle = "Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP{\textquoteright}23)",
address = "United States",
note = "IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP ; Conference date: 04-06-2023 Through 10-06-2023",
}