• Chandana B
• B Shraddha Shetty
• Kavya
• Lavanya A
• Dr Jithendra PR Nayak

This work proposes a smart system for detecting emotions from audio input, capable of analyzing either live-recorded or uploaded speech to determine emotional tone and recommend music accordingly. The system uses deep learning models and sophisticated signal processing techniques to extract pertinent auditory data like pitch, energy, and spectral qualities in order to categorize emotions like happy, sorrow, rage, and neutrality. When an emotion is detected, a music recommendation engine correlates the user's emotional state with a carefully chosen selection of songs that fit their mood, improving user experience and emotional control. Applications for the suggested system include human-computer interaction, mental health monitoring, and individualized entertainment. It provides a fun link between music therapy and affective computing. The results of the experiment show that users are satisfied with emotion-matched music playback and that emotion categorization accuracy is good.

Emotion recognition, speech analysis, music recommendation, deep learning, affective computing

"EMOTION-BASED MUSIC RECOMMENDATION SYSTEM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 7, page no.252-258, July-2025, Available :http://www.jetir.org/papers/JETIRGX06046.pdf

"EMOTION-BASED MUSIC RECOMMENDATION SYSTEM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 7, page no. pp252-258, July-2025, Available at : http://www.jetir.org/papers/JETIRGX06046.pdf