MétaCan
Menu
Back to cohort
Record W4389191800 · doi:10.22215/etd/2023-15803

Differentiation of Dry and Wet Cough Sounds using A Deep Learning Model and Data Augmentation

2023· dissertation· en· W4389191800 on OpenAlexafffund
Saiful Huq

Bibliographic record

Venuenot available
Typedissertation
Languageen
FieldComputer Science
TopicSpeech Recognition and Synthesis
Canadian institutionsCarleton University
FundersAGE-WELL
KeywordsReverberationDry coughNoise (video)Computer scienceSpeech recognitionDeep learningTask (project management)Artificial intelligenceTest dataTraining setMachine learningPattern recognition (psychology)Image (mathematics)EngineeringMedicine

Abstract

fetched live from OpenAlex

Automated classification of cough sounds has increased in importance, partly due to the worldwide COVID19 pandemic. To train such classification models requires a large dataset of cough sounds; however, it remains challenging to find sufficient expert-labelled training data. This thesis explores a novel form of audio data augmentation, where training cough sounds are corrupted with varying levels of reverberation and Gaussian noise. The combination of noise and reverberation is more effective than traditional image-based augmentation techniques and either noise or reverberation alone, leading to near-human accuracy on a wet vs. dry cough classification task using a ResNet18 model across two cough datasets. Alignment between the training and testing environments is examined using the Speech Commands audio dataset. While models trained with the closest reverb and noise level to the test environment gave the best results, the proposed audio augmentation technique produces models with robust performance across test environments.

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 distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.988
Threshold uncertainty score0.533

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.081
GPT teacher head0.328
Teacher spread0.247 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

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".

Quick stats

Citations1
Published2023
Admission routes2
Has abstractyes

Explore more

Same topicSpeech Recognition and SynthesisFrench-language works237,207