RepAugment: Input-Agnostic Representation-Level Augmentation for Respiratory Sound Classification
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917658014777344 |
|---|---|
| author | Kim, June-Woo Toikkanen, Miika Bae, Sangmin Kim, Minseok Jung, Ho-Young |
| author_facet | Kim, June-Woo Toikkanen, Miika Bae, Sangmin Kim, Minseok Jung, Ho-Young |
| contents | Recent advancements in AI have democratized its deployment as a healthcare assistant. While pretrained models from large-scale visual and audio datasets have demonstrably generalized to this task, surprisingly, no studies have explored pretrained speech models, which, as human-originated sounds, intuitively would share closer resemblance to lung sounds. This paper explores the efficacy of pretrained speech models for respiratory sound classification. We find that there is a characterization gap between speech and lung sound samples, and to bridge this gap, data augmentation is essential. However, the most widely used augmentation technique for audio and speech, SpecAugment, requires 2-dimensional spectrogram format and cannot be applied to models pretrained on speech waveforms. To address this, we propose RepAugment, an input-agnostic representation-level augmentation technique that outperforms SpecAugment, but is also suitable for respiratory sound classification with waveform pretrained models. Experimental results show that our approach outperforms the SpecAugment, demonstrating a substantial improvement in the accuracy of minority disease classes, reaching up to 7.14%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_02996 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RepAugment: Input-Agnostic Representation-Level Augmentation for Respiratory Sound Classification Kim, June-Woo Toikkanen, Miika Bae, Sangmin Kim, Minseok Jung, Ho-Young Sound Artificial Intelligence Audio and Speech Processing Recent advancements in AI have democratized its deployment as a healthcare assistant. While pretrained models from large-scale visual and audio datasets have demonstrably generalized to this task, surprisingly, no studies have explored pretrained speech models, which, as human-originated sounds, intuitively would share closer resemblance to lung sounds. This paper explores the efficacy of pretrained speech models for respiratory sound classification. We find that there is a characterization gap between speech and lung sound samples, and to bridge this gap, data augmentation is essential. However, the most widely used augmentation technique for audio and speech, SpecAugment, requires 2-dimensional spectrogram format and cannot be applied to models pretrained on speech waveforms. To address this, we propose RepAugment, an input-agnostic representation-level augmentation technique that outperforms SpecAugment, but is also suitable for respiratory sound classification with waveform pretrained models. Experimental results show that our approach outperforms the SpecAugment, demonstrating a substantial improvement in the accuracy of minority disease classes, reaching up to 7.14%. |
| title | RepAugment: Input-Agnostic Representation-Level Augmentation for Respiratory Sound Classification |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2405.02996 |