Acoustic Scene Classification Using CNN-GRU Model Without Knowledge Distillation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911151210627072 |
|---|---|
| author | Tan, Ee-Leng Yeow, Jun Wei Peksi, Santi Li, Haowen Yang, Ziyi Gan, Woon-Seng |
| author_facet | Tan, Ee-Leng Yeow, Jun Wei Peksi, Santi Li, Haowen Yang, Ziyi Gan, Woon-Seng |
| contents | In this technical report, we present the SNTL-NTU team's Task 1 submission for the Low-Complexity Acoustic Scenes and Events (DCASE) 2025 challenge. This submission departs from the typical application of knowledge distillation from a teacher to a student model, aiming to achieve high performance with limited complexity. The proposed model is based on a CNN-GRU model and is trained solely using the TAU Urban Acoustic Scene 2022 Mobile development dataset, without utilizing any external datasets, except for MicIRP, which is used for device impulse response (DIR) augmentation. The proposed model has a memory usage of 114.2KB and requires 10.9M muliply-and-accumulate (MAC) operations. Using the development dataset, the proposed model achieved an accuracy of 60.25%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_09931 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Acoustic Scene Classification Using CNN-GRU Model Without Knowledge Distillation Tan, Ee-Leng Yeow, Jun Wei Peksi, Santi Li, Haowen Yang, Ziyi Gan, Woon-Seng Audio and Speech Processing In this technical report, we present the SNTL-NTU team's Task 1 submission for the Low-Complexity Acoustic Scenes and Events (DCASE) 2025 challenge. This submission departs from the typical application of knowledge distillation from a teacher to a student model, aiming to achieve high performance with limited complexity. The proposed model is based on a CNN-GRU model and is trained solely using the TAU Urban Acoustic Scene 2022 Mobile development dataset, without utilizing any external datasets, except for MicIRP, which is used for device impulse response (DIR) augmentation. The proposed model has a memory usage of 114.2KB and requires 10.9M muliply-and-accumulate (MAC) operations. Using the development dataset, the proposed model achieved an accuracy of 60.25%. |
| title | Acoustic Scene Classification Using CNN-GRU Model Without Knowledge Distillation |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2509.09931 |