Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Voices of the Mountains: Deep Learning-Based Vocal Error Detection System for Kurdish Maqams

Darvan Shvan Khairaldeen, Hossein Hassani

TL;DR

A two-headed CNN-BiLSTM with attention mode to decide whether a window contains an error and to classify it based on the chosen errors, and a better performance on common error types shows that the method works, while the poor modal-drift recall shows that more data and balancing are needed.

Abstract

Maqam, a singing type, is a significant component of Kurdish music. A maqam singer receives training in a traditional face-to-face or through self-training. Automatic Singing Assessment (ASA) uses machine learning (ML) to provide the accuracy of singing styles and can help learners to improve their performance through error detection. Currently, the available ASA tools follow Western music rules. The musical composition requires all notes to stay within their expected pitch range from start to finish. The system fails to detect micro-intervals and pitch bends, so it identifies Kurdish maqam singing as incorrect even though the singer performs according to traditional rules. Kurdish maqam requires recognizing performance errors within microtonal spaces, which is beyond Western equal temperament. This research is the first attempt to address the mentioned gap. While many error types happen during singing, our focus is on pitch, rhythm, and modal stability errors in the context of Bayati-Kurd. We collected 50 songs from 13 vocalists ( 2-3 hours) and annotated 221 error spans (150 fine pitch, 46 rhythm, 25 modal drift). The data was segmented into 15,199 overlapping windows and converted to log-mel spectrograms. We developed a two-headed CNN-BiLSTM with attention mode to decide whether a window contains an error and to classify it based on the chosen errors. Trained for 20 epochs with early stopping at epoch 10, the model reached a validation macro-F1 of 0.468. On the full 50-song evaluation at a 0.750 threshold, recall was 39.4% and precision 25.8% . Within detected windows, type macro-F1 was 0.387, with F1 of 0.492 (fine pitch), 0.536 (rhythm), and 0.133 (modal drift); modal drift recall was 8.0%. The better performance on common error types shows that the method works, while the poor modal-drift recall shows that more data and balancing are needed.

Voices of the Mountains: Deep Learning-Based Vocal Error Detection System for Kurdish Maqams

TL;DR

A two-headed CNN-BiLSTM with attention mode to decide whether a window contains an error and to classify it based on the chosen errors, and a better performance on common error types shows that the method works, while the poor modal-drift recall shows that more data and balancing are needed.

Abstract

Maqam, a singing type, is a significant component of Kurdish music. A maqam singer receives training in a traditional face-to-face or through self-training. Automatic Singing Assessment (ASA) uses machine learning (ML) to provide the accuracy of singing styles and can help learners to improve their performance through error detection. Currently, the available ASA tools follow Western music rules. The musical composition requires all notes to stay within their expected pitch range from start to finish. The system fails to detect micro-intervals and pitch bends, so it identifies Kurdish maqam singing as incorrect even though the singer performs according to traditional rules. Kurdish maqam requires recognizing performance errors within microtonal spaces, which is beyond Western equal temperament. This research is the first attempt to address the mentioned gap. While many error types happen during singing, our focus is on pitch, rhythm, and modal stability errors in the context of Bayati-Kurd. We collected 50 songs from 13 vocalists ( 2-3 hours) and annotated 221 error spans (150 fine pitch, 46 rhythm, 25 modal drift). The data was segmented into 15,199 overlapping windows and converted to log-mel spectrograms. We developed a two-headed CNN-BiLSTM with attention mode to decide whether a window contains an error and to classify it based on the chosen errors. Trained for 20 epochs with early stopping at epoch 10, the model reached a validation macro-F1 of 0.468. On the full 50-song evaluation at a 0.750 threshold, recall was 39.4% and precision 25.8% . Within detected windows, type macro-F1 was 0.387, with F1 of 0.492 (fine pitch), 0.536 (rhythm), and 0.133 (modal drift); modal drift recall was 8.0%. The better performance on common error types shows that the method works, while the poor modal-drift recall shows that more data and balancing are needed.
Paper Structure (14 sections, 8 figures, 7 tables)

This paper contains 14 sections, 8 figures, 7 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Automatic Singing Assessment
  4. Microtonal and Maqam-Based Studies
  5. Method
  6. Results and Discussion
  7. Experimental Setup
  8. Annotation Tool Development
  9. Collected Data
  10. Dataset Preparation
  11. Training Results
  12. Evaluation Results
  13. Analysis and Discussion
  14. Conclusion and Future Work

Figures (8)

  • Figure 1: Overview of the research design we decided to use in this study.
  • Figure 2: The three error types: (a) fine pitch; (b) rhythm; (c) modal drift.
  • Figure 3: Model architecture with CNN feature extractor, bidirectional LSTM encoder, attention pooling, and two-task output heads.
  • Figure 4: The Vocal Annotator interface used for creating training annotations.
  • Figure 5: Example JSON annotation exported from the Vocal Annotator.
  • ...and 3 more figures