• Sanskar Shimpi
• Atharwa Vatsyayan

We present a technical description and evaluation of a mood-based music recommendation system that fuses realtime speech/text emotion recognition with contextual signals (time, location, weather). The system integrates (i) a streaming ASR module for speech → text, (ii) a textual emotion/sentiment estimator as a baseline, (iii) a context fusion module, and (iv) a hierarchical recommender that produces ranked music suggestions. This manuscript formalizes the problem, details signal processing and algorithmic choices, presents evaluation metrics and experimental protocol, and reports the primary empirical numbers from the project report. The project report is the primary source for the system implementation and results

mood detection, music recommendation, sentiment analysis, speech recognition, context fusion, evaluation metrics

"Mood-Based Music Recommendation System: A Context- and Emotion-Aware Pipeline", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 11, page no.f921-f924, November-2025, Available :http://www.jetir.org/papers/JETIR2511631.pdf

"Mood-Based Music Recommendation System: A Context- and Emotion-Aware Pipeline", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 11, page no. ppf921-f924, November-2025, Available at : http://www.jetir.org/papers/JETIR2511631.pdf