Introduction: Asthma is a chronic airway inflammatory disease characterized by variable airflow limitation and intermittent symptoms. In well-controlled asthma, auscultation and spirometry often appear normal, making diagnosis challenging. Moreover, bronchial provocation tests carry a risk of inducing acute bronchoconstriction. This study aimed to develop a non-invasive, objective, and reproducible diagnostic method using machine learning-based lung sound analysis for the early detection of asthma, even during stable periods. Methods: We designed a machine learning algorithm to classify controlled asthma patients and healthy individuals using respiratory sounds recorded with a digital stethoscope. We enrolled 120 participants (60 asthmatic, 60 healthy). Controlled asthma was defined according to Global Initiative for Asthma (GINA) criteria and was supported by normal spirometry, no pathological auscultation findings, and no exacerbations in the past three months. A total of 3600 respiratory sound segments (each 3 s long) were obtained by dividing 90 s recordings from 120 participants (60 asthmatic, 60 healthy) into non-overlapping clips. The samples were analyzed using Mel-Frequency Cepstral Coefficients (MFCCs) and Tunable Q-Factor Wavelet Transform (TQWT). Significant features selected with ReliefF were used to train Quadratic Support Vector Machine (SVM) and Narrow Neural Network (NNN) models. Results: In 120 participants, pulmonary function test (PFT) results in the asthma group showed lower FEV1 (86.9 ± 5.7%) and FEV1/FVC ratios (86.1 ± 8.8%) compared to controls, but remained within normal ranges. Quadratic SVM achieved 99.86% accuracy, correctly classifying 99.44% of controls and 99.89% of asthma cases. Narrow Neural Network achieved 99.63% accuracy. Sensitivity, specificity, and F1-scores exceeded 99%. Conclusion: This machine learning-based algorithm provides accurate asthma diagnosis, even in patients with normal spirometry and clinical findings, offering a non-invasive and efficient diagnostic tool.