Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Phrase-based Rāga Recognition Using Vector Space Modeling

35 views

Published on

More info: http://mtg.upf.edu/node/3425

Abstract: Automatic rāga recognition is one of the fundamental computational tasks in Indian art music. Motivated by the way seasoned listeners identify rāgas, we propose a rāga recognition approach based on melodic phrases. Firstly, we extract melodic patterns from a collection of audio recordings in an unsupervised way. Next, we group similar patterns by exploiting complex networks concepts and techniques. Drawing an analogy to topic modeling in text classification, we then represent audio recordings using a vector space model. Finally, we employ a number of classification strategies to build a predictive model for rāga recognition. To evaluate our approach, we compile a music collection of over 124 hours, comprising 480 recordings and 40 rāgas. We obtain 70% accuracy with the full 40-rāga collection, and up to 92% accuracy with its 10-rāga subset. We show that phrase-based rāga recognition is a successful strategy, on par with the state of the art, and sometimes outperforms it. A by-product of our approach, which arguably is as important as the task of rāga recognition, is the identification of rāga-phrases. These phrases can be used as a dictionary of semantically-meaningful melodic units for several computational tasks in Indian art music.

Published in: Education
  • Be the first to comment

  • Be the first to like this

Phrase-based Rāga Recognition Using Vector Space Modeling

  1. 1. Phrase-based Rāga Recognition using Vector Space Modeling Sankalp Gulati*, Joan Serrà^, Vignesh Ishwar*, Sertan Şentürk* and Xavier Serra* The 41st IEEE International Conference on Acoustics, Speech and Signal Processing Shanghai, China, 2016 *Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain ^Telefonica Research, Barcelona, Spain
  2. 2. Indian Art Music
  3. 3. Indian Art Music Indian subcontinent: India, Pakistan, Bangladesh, Srilanka, Nepal and Bhutan
  4. 4. Indian Art Music
  5. 5. Indian Art Music: Hindustani music
  6. 6. Indian Art Music: Carnatic music
  7. 7. Rāga: melodic framework q  Grammar for improvisation and composition
  8. 8. Automatic Rāga Recognition Training corpus Rāga recognition System Rāga label Yaman Shankarabharnam Todī Darbari Kalyan Bageśrī Kambhojī Hamsadhwani Des Harikambhoji Kirvani Atana Behag Kapi Begada
  9. 9. Rāga Characterization: Svaras time (s) 10 30
  10. 10. Rāga Characterization: Svaras time (s) 10 30
  11. 11. Rāga Characterization: Svaras 50 100 150 200 250 300 0 0.2 0.4 0.6 0.8 1 Frequency (bins), 1 bin = 10 Cents, Ref = 55 Hz Normalizedsalience Lower Sa Tonic middle Sa Higher Sa Frequency (cents), fref = tonic frequency 0 120-120 q  P. Chordia and S. Şentürk, “Joint recognition of raag and tonic in North Indian music,” Computer Music Journal, vol. 37, no. 3, pp. 82–98, 2013. q  G. K. Koduri, S. Gulati, P. Rao, and X. Serra, “Rāga recognition based on pitch distribution methods,” Journal of New Music Research, vol. 41, no. 4, pp. 337–350, 2012. time (s) 10 30
  12. 12. Rāga Characterization: Intonation 50 100 150 200 250 300 0 0.2 0.4 0.6 0.8 1 Frequency (bins), 1 bin = 10 Cents, Ref = 55 Hz Normalizedsalience Lower Sa Tonic middle Sa Higher Sa Frequency (cents), fref = tonic frequency 0 120-120 time (s) 10 30
  13. 13. Rāga Characterization: Intonation 50 100 150 200 250 300 0 0.2 0.4 0.6 0.8 1 Frequency (bins), 1 bin = 10 Cents, Ref = 55 Hz Normalizedsalience Lower Sa Tonic middle Sa Higher Sa Frequency (cents), fref = tonic frequency 0 120-120 q  G.K.Koduri,V.Ishwar,J.Serrà,andX.Serra,“Intonation analysis of rāgas in Carnatic music,” Journal of New Music Research, vol. 43, no. 1, pp. 72–93, 2014. q  H. G. Ranjani, S. Arthi, and T. V. Sreenivas, “Carnatic music analysis: Shadja, swara identification and raga verification in alapana using stochastic models,” in IEEE WASPAA, 2011, pp. 29–32. time (s) 10 30
  14. 14. Rāga Characterization: Ārōh-Avrōh q  Ascending-descending svara pattern; melodic progression time (s) 10 30
  15. 15. time (s) 10 30 Rāga Characterization: Ārōh-Avrōh q  S. Shetty and K. K. Achary, “Raga mining of indian music by extracting arohana-avarohana pattern,” Int. Journal of Recent Trends in Engineering, vol. 1, no. 1, pp. 362–366, 2009. q  V. Kumar, H Pandya, and C. V. Jawahar, “Identifying ragas in indian music,” in 22nd Int. Conf. on Pattern Recognition (ICPR), 2014, pp. 767–772. q  P. V. Rajkumar, K. P. Saishankar, and M. John, “Identification of Carnatic raagas using hidden markov models,” in IEEE 9th Int. Symposium on Applied Machine Intelligence and Informatics (SAMI), 2011, pp. 107–110. Melodic Progression Templates N-gram Distribution Hidden Markov Model
  16. 16. Rāga Characterization: Melodic motifs time (s) 10 30
  17. 17. time (s) 10 30 Rāga Characterization: Melodic motifs q  R. Sridhar and T. V. Geetha, “Raga identification of carnatic music for music information retrieval,” International Journal of Recent Trends in Engineering, vol. 1, no. 1, pp. 571–574, 2009. q  S. Dutta, S. PV Krishnaraj, and H. A. Murthy, “Raga verification in carnatic music using longest common segment set,” in Int. Soc. for Music Information Retrieval Conf. (ISMIR), pp. 605-611,2015 Rāga A Rāga B Rāga C
  18. 18. Goal q  Automatic rāga recognition Training corpus Rāga recognition System Rāga label Yaman Shankarabharnam Todī Darbari Kalyan Bageśrī Kambhojī Hamsadhwani Des Harikambhoji Kirvani Atana Behag Kapi Begada
  19. 19. Goal q  Automatic rāga recognition Training corpus Rāga recognition System Rāga label time (s) 10 time (s) 10 time (s) 30 time (s) 10 time (s) 10 time (s) 30 time (s 10 time (s) 10 time (s) 30 time 10 time (s 10 time (s) 30 tim 10 time ( 10 time (s) 0 30 tim 10 time 10 time (s) 10 30 t 10 tim 10 time (s) 10 30 10 ti 10 time (s) 10 30 1010 time (s) 10 30 1010 time (s) 10 30 1010 time (s) 10 30 1010 time (s) 10 30 1010 time (s) 10 30 1010 time (s) 10 30 1010 time (s) 10 30 Yaman Shankarabharnam Todī Darbari Kalyan Bageśrī Kambhojī Hamsadhwani Des Harikambhoji Kirvani Atana Behag Kapi Begada time (s) 10 30 time (s) 10 30 30
  20. 20. Block Diagram: Proposed Approach Inter-recording Pattern Detection Intra-recording Pattern Discovery Data Processing Pattern Network Generation Similarity Thresholding Community Detection Carnatic music collection Melodic Pattern Discovery Melodic Pattern Clustering Vocabulary Extraction Term-frequency Feature Extraction Feature Normalization Feature Extraction Feature Matrix
  21. 21. Block Diagram: Pattern Discovery Inter-recording Pattern Detection Intra-recording Pattern Discovery Data Processing Pattern Network Generation Similarity Thresholding Community Detection Carnatic music collection Melodic Pattern Discovery Melodic Pattern Clustering Vocabulary Extraction Term-frequency Feature Extraction Feature Normalization Feature Extraction Feature Matrix
  22. 22. Block Diagram: Pattern Clustering Inter-recording Pattern Detection Intra-recording Pattern Discovery Data Processing Pattern Network Generation Similarity Thresholding Community Detection Carnatic music collection Melodic Pattern Discovery Melodic Pattern Clustering Vocabulary Extraction Term-frequency Feature Extraction Feature Normalization Feature Extraction Feature Matrix
  23. 23. Block Diagram: Feature Extraction Inter-recording Pattern Detection Intra-recording Pattern Discovery Data Processing Pattern Network Generation Similarity Thresholding Community Detection Carnatic music collection Melodic Pattern Discovery Melodic Pattern Clustering Vocabulary Extraction Term-frequency Feature Extraction Feature Normalization Feature Extraction Feature Matrix
  24. 24. Block Diagram: Pattern Discovery Inter-recording Pattern Detection Intra-recording Pattern Discovery Data Processing Pattern Network Generation Similarity Thresholding Community Detection Carnatic music collection Melodic Pattern Discovery Melodic Pattern Clustering Vocabulary Extraction Term-frequency Feature Extraction Feature Normalization Feature Extraction Feature Matrix
  25. 25. Block Diagram: Pattern Discovery Inter-recording Pattern Detection Intra-recording Pattern Discovery Data Processing Pattern Network Generation Similarity Thresholding Community Detection Carnatic music collection Melodic Pattern Discovery Melodic Pattern Clustering Vocabulary Extraction Term-frequency Feature Extraction Feature Normalization Feature Extraction Feature Matrix S. Gulati, J. Serrà, V. Ishwar, and X. Serra, “Mining melodic patterns in large audio collections of Indian art music,” in Int. Conf. on Signal Image Technology & Internet Based Systems - MIRA, Marrakesh, Morocco, 2014, pp. 264–271.
  26. 26. Proposed Approach: Pattern Discovery -Predominant pitch estimation -Downsampling -Hz to Cents -Tonic normalization -Brute-force segmentation -Segment filtering -Uniform Time-scaling Flat Non-flat Inter-recording Pattern Detection Intra-recording Pattern Discovery Data Processing
  27. 27. Proposed Approach: Pattern Discovery Inter-recording Pattern Detection Intra-recording Pattern Discovery Data Processing Seed Patterns Recording 1 Recording 2 Recording N
  28. 28. Proposed Approach: Pattern Discovery Inter-recording Pattern Detection Intra-recording Pattern Discovery Data Processing Inter-recording search Rank-refinement
  29. 29. Block Diagram: Pattern Clustering Inter-recording Pattern Detection Intra-recording Pattern Discovery Data Processing Pattern Network Generation Similarity Thresholding Community Detection Carnatic music collection Melodic Pattern Discovery Melodic Pattern Clustering Vocabulary Extraction Term-frequency Feature Extraction Feature Normalization Feature Extraction Feature Matrix
  30. 30. Proposed Approach: Pattern Clustering q  M. EJ Newman, “The structure and function of complex networks,” Society for Industrial and Applied Mathematics (SIAM) review, vol. 45, no. 2, pp. 167–256, 2003. Pattern Network Generation Similarity Thresholding Community Detection Undirectional
  31. 31. Proposed Approach: Pattern Clustering q  M. EJ Newman, “The structure and function of complex networks,” Society for Industrial and Applied Mathematics (SIAM) review, vol. 45, no. 2, pp. 167–256, 2003. q  S. Maslov and K. Sneppen, “Specificity and stability in topology of protein networks,” Science, vol. 296, no. 5569, pp. 910– 913, 2002. Pattern Network Generation Similarity Thresholding Community Detection Ts *
  32. 32. Proposed Approach: Pattern Clustering q  V. D. Blondel, J. L. Guillaume, R. Lambiotte, and E. Lefebvre, “Fast unfolding of communities in large networks,” Journal of Statistical Mechanics: Theory and Experiment, vol. 2008, no. 10, pp. P10008, 2008. q  S Fortunato, “Community detection in graphs,” Physics Reports, vol. 486, no. 3, pp. 75–174, 2010. Pattern Network Generation Similarity Thresholding Community Detection
  33. 33. Proposed Approach: Pattern Clustering Pattern Network Generation Similarity Thresholding Community Detection q  V. D. Blondel, J. L. Guillaume, R. Lambiotte, and E. Lefebvre, “Fast unfolding of communities in large networks,” Journal of Statistical Mechanics: Theory and Experiment, vol. 2008, no. 10, pp. P10008, 2008. q  S Fortunato, “Community detection in graphs,” Physics Reports, vol. 486, no. 3, pp. 75–174, 2010.
  34. 34. Block Diagram: Feature Extraction Inter-recording Pattern Detection Intra-recording Pattern Discovery Data Processing Pattern Network Generation Similarity Thresholding Community Detection Carnatic music collection Melodic Pattern Discovery Melodic Pattern Clustering Vocabulary Extraction Term-frequency Feature Extraction Feature Normalization Feature Extraction Feature Matrix
  35. 35. Proposed Approach: Feature Extraction
  36. 36. Proposed Approach: Feature Extraction Text/document classification Phrases Rāga Recordings Words Topic Documents
  37. 37. Proposed Approach: Feature Extraction Text/document classification Term Frequency Inverse Document Frequency (TF-IDF)
  38. 38. Proposed Approach: Feature Extraction Vocabulary Extraction Term-frequency Feature Extraction Feature Normalization
  39. 39. Proposed Approach: Feature Extraction Vocabulary Extraction Term-frequency Feature Extraction Feature Normalization
  40. 40. Proposed Approach: Feature Extraction Vocabulary Extraction Term-frequency Feature Extraction Feature Normalization
  41. 41. Proposed Approach: Feature Extraction 1 0 4 2 2 0 1 1 0 3 3 3 Vocabulary Extraction Term-frequency Feature Extraction Feature Normalization
  42. 42. Proposed Approach: Feature Extraction Vocabulary Extraction Term-frequency Feature Extraction Feature Normalization
  43. 43. Proposed Approach: Feature Extraction Vocabulary Extraction Term-frequency Feature Extraction Feature Normalization F1(p, r) = 1, if f(p, r) > 0 0, otherwise F2(p, r) = f(p, r) F3(p, r) = f(p, r) × irf(p, R) irf(p, R) = log N |{r ∈ R : p ∈ r}|
  44. 44. Proposed Approach: Feature Extraction Vocabulary Extraction Term-frequency Feature Extraction Feature Normalization F1(p, r) = 1, if f(p, r) > 0 0, otherwise F2(p, r) = f(p, r) F3(p, r) = f(p, r) × irf(p, R) irf(p, R) = log N |{r ∈ R : p ∈ r}| F1(p, r) = 1, if f(p, r) > 0 0, otherwise (1) F2(p, r) = f(p, r) (2) F3(p, r) = f(p, r) × irf(p, R) (3) irf(p, R) = log N |{r ∈ R : p ∈ r}| (4)
  45. 45. Proposed Approach: Feature Extraction Vocabulary Extraction Term-frequency Feature Extraction Feature Normalization F1(p, r) = 1, if f(p, r) > 0 0, otherwise F2(p, r) = f(p, r) F3(p, r) = f(p, r) × irf(p, R) irf(p, R) = log N |{r ∈ R : p ∈ r}| F1(p, r) = 1, if f(p, r) > 0 0, otherwise (1) F2(p, r) = f(p, r) (2) F3(p, r) = f(p, r) × irf(p, R) (3) irf(p, R) = log N |{r ∈ R : p ∈ r}| (4) F1(p, r) = 1, if f(p, r) > 0 0, otherwise F2(p, r) = f(p, r) F3(p, r) = f(p, r) × irf(p, R) irf(p, R) = log N |{r ∈ R : p ∈ r}| F1(p, r) = 1, if f(p, r) > 0 0, otherwise F2(p, r) = f(p, r) F3(p, r) = f(p, r) × irf(p, R) irf(p, R) = log N |{r ∈ R : p ∈ r}|
  46. 46. Evaluation: Music Collection
  47. 47. Evaluation: Music Collection q  Corpus: CompMusic Carnatic music §  Commercial released music (~325) CDs §  Metadata available in Musicbrainz MusicBrainz
  48. 48. Evaluation: Music Collection q  Corpus: CompMusic Carnatic music §  Commercial released music (~325) CDs §  Metadata available in Musicbrainz q  Datasets: subsets of corpus §  DB40rāga ¨  480 audio recordings, 124 hours of music ¨  40 diverse set of rāgas ¨  310 compositions, 62 unique artists §  DB10rāga ¨  10 rāga subset of DB40rāga MusicBrainz
  49. 49. Evaluation: Music Collection q  Corpus: CompMusic Carnatic music §  Commercial released music (~325) CDs §  Metadata available in Musicbrainz q  Datasets: subsets of corpus §  DB40rāga ¨  480 audio recordings, 124 hours of music ¨  40 diverse set of rāgas ¨  310 compositions, 62 unique artists §  DB10rāga ¨  10 rāga subset of DB40rāga MusicBrainz h#p://compmusic.upf.edu/node/278
  50. 50. Evaluation: Classification methodology q  Experimental setup §  Stratified 12-fold cross validation (balanced) §  Repeat experiment 20 times §  Evaluation measure: mean classification accuracy
  51. 51. Evaluation: Classification methodology q  Experimental setup §  Stratified 12-fold cross validation (balanced) §  Repeat experiment 20 times §  Evaluation measure: mean classification accuracy q  Classifiers §  Multinomial, Gaussian and Bernoulli naive Bayes (NBM, NBG and NBB) §  SVM with a linear and RBF-kernel, and with a SGD learning (SVML, SVMR and SGD) §  logistic regression (LR) and random forest (RF)
  52. 52. Evaluation: Classification methodology q  Statistical significance §  Mann-Whitney U test (p < 0.01) §  Multiple comparisons: Holm Bonferroni method q  H. B. Mann and D. R. Whitney, “On a test of whether one of two random variables is stochastically larger than the other,” The annals of mathematical statistics, vol. 18, no. 1, pp. 50–60, 1947. q  S. Holm, “A simple sequentially rejective multiple test procedure,” Scandinavian journal of statistics, vol. 6, no. 2, pp. 65–70, 1979.
  53. 53. Evaluation: Classification methodology q  Statistical significance §  Mann-Whitney U test (p < 0.01) §  Multiple comparisons: Holm Bonferroni method q  Comparison with the state-of-the-art §  S1: Pitch-class-distribution (PCD)-based method (PCD120, PCDfull) §  S2: Parameterized (PCD)-based method (PCDparam) q  H. B. Mann and D. R. Whitney, “On a test of whether one of two random variables is stochastically larger than the other,” The annals of mathematical statistics, vol. 18, no. 1, pp. 50–60, 1947. q  S. Holm, “A simple sequentially rejective multiple test procedure,” Scandinavian journal of statistics, vol. 6, no. 2, pp. 65–70, 1979. q  P. Chordia and S. Şentürk, “Joint recognition of raag and tonic in North Indian music,” Computer Music Journal, vol. 37, no. 3, pp. 82–98, 2013. q  G.K.Koduri,V.Ishwar,J.Serrà,andX.Serra,“Intonation analysis of rāgas in Carnatic music,” Journal of New Music Research, vol. 43, no. 1, pp. 72–93, 2014.
  54. 54. Results e a - e t r - t ) ) e db Mtd Ftr NBM NBB LR SVML 1NN DB10r¯aga M F1 90.6 74 84.1 81.2 - F2 91.7 73.8 84.8 81.2 - F3 90.5 74.5 84.3 80.7 - S1 PCD120 - - - - 82.2 PCDfull - - - - 89.5 S2 PDparam 37.9 11.2 70.1 65.7 - DB40r¯aga M F1 69.6 61.3 55.9 54.6 - F2 69.6 61.7 55.7 54.3 - F3 69.5 61.5 55.9 54.5 - S1 PCD120 - - - - 66.4 PCDfull - - - - 74.1 S2 PDparam 20.8 2.6 51.4 44.2 - Table 1. Accuracy (in percentage) of different methods (Mtd) for
  55. 55. Results e a - e t r - t ) ) e db Mtd Ftr NBM NBB LR SVML 1NN DB10r¯aga M F1 90.6 74 84.1 81.2 - F2 91.7 73.8 84.8 81.2 - F3 90.5 74.5 84.3 80.7 - S1 PCD120 - - - - 82.2 PCDfull - - - - 89.5 S2 PDparam 37.9 11.2 70.1 65.7 - DB40r¯aga M F1 69.6 61.3 55.9 54.6 - F2 69.6 61.7 55.7 54.3 - F3 69.5 61.5 55.9 54.5 - S1 PCD120 - - - - 66.4 PCDfull - - - - 74.1 S2 PDparam 20.8 2.6 51.4 44.2 - Table 1. Accuracy (in percentage) of different methods (Mtd) for
  56. 56. Results e a - e t r - t ) ) e db Mtd Ftr NBM NBB LR SVML 1NN DB10r¯aga M F1 90.6 74 84.1 81.2 - F2 91.7 73.8 84.8 81.2 - F3 90.5 74.5 84.3 80.7 - S1 PCD120 - - - - 82.2 PCDfull - - - - 89.5 S2 PDparam 37.9 11.2 70.1 65.7 - DB40r¯aga M F1 69.6 61.3 55.9 54.6 - F2 69.6 61.7 55.7 54.3 - F3 69.5 61.5 55.9 54.5 - S1 PCD120 - - - - 66.4 PCDfull - - - - 74.1 S2 PDparam 20.8 2.6 51.4 44.2 - Table 1. Accuracy (in percentage) of different methods (Mtd) for
  57. 57. Results e a - e t r - t ) ) e db Mtd Ftr NBM NBB LR SVML 1NN DB10r¯aga M F1 90.6 74 84.1 81.2 - F2 91.7 73.8 84.8 81.2 - F3 90.5 74.5 84.3 80.7 - S1 PCD120 - - - - 82.2 PCDfull - - - - 89.5 S2 PDparam 37.9 11.2 70.1 65.7 - DB40r¯aga M F1 69.6 61.3 55.9 54.6 - F2 69.6 61.7 55.7 54.3 - F3 69.5 61.5 55.9 54.5 - S1 PCD120 - - - - 66.4 PCDfull - - - - 74.1 S2 PDparam 20.8 2.6 51.4 44.2 - Table 1. Accuracy (in percentage) of different methods (Mtd) for
  58. 58. Results e a - e t r - t ) ) e db Mtd Ftr NBM NBB LR SVML 1NN DB10r¯aga M F1 90.6 74 84.1 81.2 - F2 91.7 73.8 84.8 81.2 - F3 90.5 74.5 84.3 80.7 - S1 PCD120 - - - - 82.2 PCDfull - - - - 89.5 S2 PDparam 37.9 11.2 70.1 65.7 - DB40r¯aga M F1 69.6 61.3 55.9 54.6 - F2 69.6 61.7 55.7 54.3 - F3 69.5 61.5 55.9 54.5 - S1 PCD120 - - - - 66.4 PCDfull - - - - 74.1 S2 PDparam 20.8 2.6 51.4 44.2 - Table 1. Accuracy (in percentage) of different methods (Mtd) for
  59. 59. Error Analysis Kalyāṇi Varāḷi Tōḍi Pūrvikalyāṇi
  60. 60. Error Analysis Allied rāgas
  61. 61. Error Analysis: complementary with S1 M (F1) S1 (PCDfull)
  62. 62. Summary
  63. 63. Summary q  Phrase-based rāga recognition using VSM is a successful strategy
  64. 64. Summary q  Phrase-based rāga recognition using VSM is a successful strategy q  Mere presence/absence of melodic phrases is enough to recognize rāga
  65. 65. Summary q  Phrase-based rāga recognition using VSM is a successful strategy q  Mere presence/absence of melodic phrases enough to recognize rāga q  Multinomial Naive Bayes classifier outperforms the rest
  66. 66. Summary q  Phrase-based rāga recognition using VSM is a successful strategy q  Mere presence/absence of melodic phrases enough to recognize rāga q  Multinomial Naive Bayes classifier outperforms the rest q  Topological properties of network - similarity threshold
  67. 67. Summary q  Phrase-based rāga recognition using VSM is a successful strategy q  Mere presence/absence of melodic phrases enough to recognize rāga q  Multinomial Naive Bayes classifier outperforms the rest q  Topological properties of network - similarity threshold q  Complementary errors in prediction compared to PCD-based methods (Future Work)
  68. 68. Resources q  Rāga dataset: §  http://compmusic.upf.edu/node/278 q  Demo: §  http://dunya.compmusic.upf.edu/pattern_network/ q  CompMusic: §  http://compmusic.upf.edu/ q  Related datasets: §  http://compmusic.upf.edu/datasets
  69. 69. Resources q  Rāga dataset: §  http://compmusic.upf.edu/node/278 q  Demo: §  http://dunya.compmusic.upf.edu/pattern_network/ q  CompMusic: §  http://compmusic.upf.edu/ q  Related datasets: §  http://compmusic.upf.edu/datasets
  70. 70. Resources q  Rāga dataset: §  http://compmusic.upf.edu/node/278 q  Demo: §  http://dunya.compmusic.upf.edu/pattern_network/ q  CompMusic (Project): §  http://compmusic.upf.edu/ q  Related datasets: §  http://compmusic.upf.edu/datasets
  71. 71. Phrase-based Rāga Recognition using Vector Space Modeling Sankalp Gulati*, Joan Serrà^, Vignesh Ishwar*, Sertan Şentürk* and Xavier Serra* The 41st IEEE International Conference on Acoustics, Speech and Signal Processing Shanghai, China, 2016 *Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain ^Telefonica Research, Barcelona, Spain

×