Paper year
2026
Paper dossier
Deep Learning-Based Emotion Recognition from Instrumental Hindi Music Signal
Detail viewSimilarity handoff
Review source metadata, abstract, authors, topics, and local similarity context before moving into explanation and ranking views.
Citations
0
Authors
0
Topic labels
0
Source readout
Source and corpus status
Venue
Unknown venue
Source slug
unknown
Corpus placement
Controlled edge slice
Similarity rows
Not available yet
Ranking readout
Where this paper lands in the current run
Ranking details could not be loaded (API 503).
Abstract
Music Emotion Recognition (MER) is an important research area within Music Information Retrieval that focuses on automatically identifying emotional characteristics conveyed by music. Although deep learning approaches have shown promising performance, most existing studies rely heavily on vocal or lyrical information and are largely based on Western music datasets. As a result, emotion recognition from instrumental Hindi music remains relatively underexplored. This paper presents a Convolutional Neural Network (CNN)-based framework for emotion recognition using instrumental (voice-removed) Hindi music from the MER500 dataset. Audio signals are converted into spectrogram representations using the Short-Time Fourier Transform and used as input to a CNN for automatic learning of discriminative spectral-temporal features. Experiments are conducted under two configurations: a five-category classification setting (Devotional, Happy, Party, Romantic, and Sad) and a four-category setting obtained by removing the Happy emotion class, which exhibits high ambiguity in instrumental music. The five-category experiment achieves an overall classification accuracy of 64% with a macro-averaged F1-score of 0.64, while excluding the Happy class improves performance to a test accuracy of 67.80% and a macro F1-score of 0.68. The results demonstrate that instrumental Hindi music contains meaningful emotional cues and emphasize the importance of emotion taxonomy design when performing emotion recognition without vocal or lyrical information. This work contributes to culturally diverse MER research and provides a foundation for future multimodal emotion recognition studies.
Authors
No authors available.
Neighborhood labels
Topics
0 labels
Topic labels are imported metadata and can be noisy; use them as coarse navigation hints, not authoritative classifications.
Neighbor surface
Similar papers
Similar papers use a separately configured neighbor embedding; it may differ from the embedding version used by the current ranked run.
No embedding-backed neighbors available for this paper/version yet.
Next handoff
Best next moves from here
01
Check recommendation families
Use Recommended to see whether this paper behaves like an emerging or undercited signal in the current ranked feed, or how it appears on the bridge preview / diagnostics view.
02
Inspect nearby topics
Use Trends to understand whether its attached labels are heating up or cooling down inside the curated corpus.
03
Cross-check evaluation baselines
Use Evaluation to compare the dossier readout against citation and recency baselines for the same resolved family run.