Résumé: Early and accurate diagnosis of thyroid disorders is essential due to their prevalence and health impact. To enhance interpretability in clinical settings, we propose a comprehensive workflow for transparent thyroid disease prediction using a multiclass classification problem with five diagnostic categories. A dataset of 9172 samples with 31 features was used to train various machine and deep learning models. A dual-layered framework combining Feature Selection (ETC, MI, RFE) and Explainable AI (SHAP, LIME) improved performance and transparency. Gradient Boosting achieved the highest accuracy (0.97). SHAP explained global feature influence, while LIME clarified individual predictions. Our approach supports interpretable, reliable AI-based diagnostic tools for thyroid disorder classification.

Résumé: ------------------ -------------------

Résumé: Speech disfluencies, such as repetitions and pro-longations common in stuttering, hinder effective interaction with voice technologies due to limitations in Automatic Speech Recognition (ASR) and Text-to-Speech (TTS) systems. This paper presents an end-to-end pipeline to transform disfluent speech into fluent, natural-sounding audio while preserving speaker identity and affective qualities. The system integrates a fine-tuned Whisper ASR model, achieving a 33% Word Error Rate (WER) reduction (from 18.5% to 12.3%), a hybrid disfluency detection framework with 89.5% accuracy, a T5-based text reconstruction module with high semantic fidelity (BLEU: 0.78, ROUGE-L: 0.82), and a zero-shot TTS stage (Bark/YourTTS) yielding fluent speech with strong speaker similarity (cosine similarity: 0.86) and naturalness (Mean Opinion Score: 4.1). Evaluated on datasets like SEP-28k and UCLASS, the system achieves real …

Résumé: ----------------------

Résumé: ------------------ -------------------

Résumé: Speech disfluencies, such as repetitions and pro-longations common in stuttering, hinder effective interaction with voice technologies due to limitations in Automatic Speech Recognition (ASR) and Text-to-Speech (TTS) systems. This paper presents an end-to-end pipeline to transform disfluent speech into fluent, natural-sounding audio while preserving speaker identity and affective qualities. The system integrates a fine-tuned Whisper ASR model, achieving a 33% Word Error Rate (WER) reduction (from 18.5% to 12.3%), a hybrid disfluency detection framework with 89.5% accuracy, a T5-based text reconstruction module with high semantic fidelity (BLEU: 0.78, ROUGE-L: 0.82), and a zero-shot TTS stage (Bark/YourTTS) yielding fluent speech with strong speaker similarity (cosine similarity: 0.86) and naturalness (Mean Opinion Score: 4.1). Evaluated on datasets like SEP-28k and UCLASS, the system achieves real …

Résumé: ----------------------

Résumé: -----------------------------