"Science is an error-correcting process." — Charles S. Peirce

• 🌱 PhD in Signal Processing and Machine Learning
• ✨ Ex-Software Engineer in Web Development

• 💻 Programming: Python, Java, JavaScript, SQL, GDScript
• ⚛️ Machine Learning: PyTorch, TensorFlow, scikit-learn, Ray Tune, MLflow
• 🗣️ Audio & NLP: librosa, torchaudio, NLTK
• 📊 Data Analysis: NumPy, SciPy, Pandas, Jupyter, Matplotlib
• 🌐 Web & Backend: Java EE, Spring, Hibernate, Django, Flask, Gradio
• 📱 GUI & Game Development: PySide6, Godot Engine
• ⚙️ Databases & DevOps: MySQL, PostgreSQL, Linux, Docker, Git

• 🧬 Audio-Text Semantic Alignment using Unsupervised Learning
• 🔎 Negative Sampling in Contrastive Learning of Audio-Text Representations
• 🦻 Subjective Evaluation of Audio-Text Semantic Relevance
• ♻️ Estimating Audio-Text Semantic Relevance through Audio Captions
• 🌐 DCASE 2025 Challenge Task 6: Language-Based Audio Retrieval
• 🌐 DCASE 2024 Challenge Task 8: Language-Based Audio Retrieval
• 🌐 DCASE 2023 Challenge Task 6: Automated Audio Captioning and Language-Based Audio Retrieval
• 🌐 DCASE 2022 Challenge Task 6: Automated Audio Captioning and Language-Based Audio Retrieval

Happy to discuss multimodal ML, applied AI, or the challenges of building scalable AI systems. Whether you're hacking on a side project, exploring new ideas, or working in research — feel free to reach out, I'd love to exchange thoughts!

📫 Email: huang.xie@outlook.com
🔗 Google Scholar: scholar.google.com/citations?user=_wmP81AAAAAJ
🔗 LinkedIn: linkedin.com/in/huang-xie-28b7872bb