Unsupervised Feature Learning for Environmental Sound Classification\n Using Weighted Cycle-Consistent Generative Adversarial Network
Bibliographic record
Abstract
In this paper we propose a novel environmental sound classification approach\nincorporating unsupervised feature learning from codebook via spherical\n$K$-Means++ algorithm and a new architecture for high-level data augmentation.\nThe audio signal is transformed into a 2D representation using a discrete\nwavelet transform (DWT). The DWT spectrograms are then augmented by a novel\narchitecture for cycle-consistent generative adversarial network. This\nhigh-level augmentation bootstraps generated spectrograms in both intra and\ninter class manners by translating structural features from sample to sample. A\ncodebook is built by coding the DWT spectrograms with the speeded-up robust\nfeature detector (SURF) and the K-Means++ algorithm. The Random Forest is our\nfinal learning algorithm which learns the environmental sound classification\ntask from the clustered codewords in the codebook. Experimental results in four\nbenchmarking environmental sound datasets (ESC-10, ESC-50, UrbanSound8k, and\nDCASE-2017) have shown that the proposed classification approach outperforms\nthe state-of-the-art classifiers in the scope, including advanced and dense\nconvolutional neural networks such as AlexNet and GoogLeNet, improving the\nclassification rate between 3.51% and 14.34%, depending on the dataset.\n
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".