New objective timbre parameters for classification of voice type and fach in professional opera singers

Müller, Matthias S.; Wang, Zehui; Caffier, Felix; Caffier, Philipp P.

doi:10.1038/s41598-022-22821-w

Cited by 4 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to facilitate the application of ML techniques for resolving the fach classification issue, a collection of 13 distinctive features were meticulously computed and extracted from the original sound files. These features include the following: For a detailed definition of these features, please refer to our previous publica [27,28]. Descriptive statistics were used to determine the basic characteristics of the dat each voice type and fach, minimum and maximum values, medians, quartiles, mean standard deviations (SD) and reference ranges (RR = M ± 1.96 × SD) were compute keep the statistical tests consistent throughout all categories, non-parametric tests (w do not rely on normality) were used whenever possible.…”

Section: Methodsmentioning

confidence: 99%

“…It includes numerous decision trees and implements random feature and selection during the training phase. The results from each decision tree are comb For a detailed definition of these features, please refer to our previous publications [27,28]. Descriptive statistics were used to determine the basic characteristics of the data.…”

Section: Methodsmentioning

confidence: 99%

“…Vocal arts medicine is using these diagnostic tools to care for and prevent professional voice disorders in performing artists [26]. In cases of recurrent or persistent voice problems, phoniatric Diagnostics 2023, 13, 2870 2 of 13 specialists are often confronted with unsolved classification questions: What is the right voice type and "Fach", lyric or dramatic [27,28]? Since the above-mentioned established examination tools do not include a connection to fach-specific requirements, the precise causes of diagnosed voice problems are currently often difficult to establish adequately.…”

Section: Introductionmentioning

confidence: 99%

“…In 2008, Ling called it anachronistic and presented a new fach classification for male voices, using "voice structure" [35] (pp. [27][28][29]66) and "voice category" [35] (pp. 257-258), among others, as a source of information.…”

Section: Introductionmentioning

confidence: 99%

“…To date, there are no internationally published studies (apart from [ 27 , 28 ]) within the fields of voice science, pedagogy, or engineering on the objective distinction between lyric and dramatic fach. The scientific literature search revealed only one paper using a ML approach to investigate a timing-based classification method for human voice in opera recordings [ 29 ].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Harnessing Machine Learning in Vocal Arts Medicine: A Random Forest Application for “Fach” Classification in Opera

Wang,

Müller,

Caffier

et al. 2023

Diagnostics

Self Cite

View full text Add to dashboard Cite

Vocal arts medicine provides care and prevention strategies for professional voice disorders in performing artists. The issue of correct “Fach” determination depending on the presence of a lyric or dramatic voice structure is of crucial importance for opera singers, as chronic overuse often leads to vocal fold damage. To avoid phonomicrosurgery or prevent a premature career end, our aim is to offer singers an improved, objective fach counseling using digital sound analyses and machine learning procedures. For this purpose, a large database of 2004 sound samples from professional opera singers was compiled. Building on this dataset, we employed a classic ensemble learning method, namely the Random Forest algorithm, to construct an efficient fach classifier. This model was trained to learn from features embedded within the sound samples, subsequently enabling voice classification as either lyric or dramatic. As a result, the developed system can decide with an accuracy of about 80% in most examined voice types whether a sound sample has a lyric or dramatic character. To advance diagnostic tools and health in vocal arts medicine and singing voice pedagogy, further machine learning methods will be applied to find the best and most efficient classification method based on artificial intelligence approaches.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Harnessing Machine Learning in Vocal Arts Medicine: A Random Forest Application for “Fach” Classification in Opera

Wang,

Müller,

Caffier

et al. 2023

Diagnostics

Self Cite

View full text Add to dashboard Cite

show abstract

Experienced Listeners’ Perception of Timbre Dissimilarity Within and Between Voice Categories

Stone¹,

Erickson²

2023

Journal of Voice

View full text Add to dashboard Cite

The Analysis of Chinese and Japanese Traditional Opera Tunes With Artificial Intelligence Technology Based on Deep Learning

Yao,

Liu

2024

IEEE Access

View full text Add to dashboard Cite

This study aims to propose a comparison model of Chinese and Japanese traditional opera tunes based on deep learning (DL) and artificial intelligence technology, which can be used to effectively analyze and classify the tune characteristics of Chinese and Japanese traditional opera. To achieve this aim, a multi-layered DL model, including Convolutional Neural Network, Long Short-Term Memory, Recurrent Neural Network, and Gated Recurrent Unit, is constructed based on the tune characteristics of Chinese and Japanese traditional opera. In the extensive experimental verification, the proposed model has achieved remarkable results in the task of classifying Chinese and Japanese traditional opera tunes. Specifically, the proposed model achieves an accuracy of 89% and 88%, recall of 88% and 87%, and F1-score of 88% and 87% in the tune classification task of the Chinese and Japanese traditional opera, respectively. Compared with similar models, the proposed model performs better in classification. INDEX TERMSChinese and Japanese traditional opera tunes; Deep learning; Artificial intelligence; Tune classification; Convolutional neural network I. INTRODUCTION A. RESEARCH BACKGROUND AND MOTIVATIONSWith the development of globalization and the swift growth of science and technology, as an important cultural heritage of China and Japan, traditional opera's protection, inheritance, and innovation have attracted more and more attention [1][2][3]. However, due to the differences between China and Japan in language, culture, history, and other aspects, the inheritance and development of Chinese and Japanese traditional operas face many challenges [4][5]. Among them, how to dig deeply and compare the tune characteristics of Chinese and Japanese traditional operas has become a topic worthy of study [6][7][8]. The tune is a vital part of traditional opera, which not only represents the opera's musical style and singing characteristics but also contains rich cultural connotations and artistic values [9-10]. The comparative analysis of Chinese and Japanese traditional opera tunes allows the similarities and differences between their traditional opera art to be better understood, thus providing references for the cross-cultural communication and inheritance of the two countries' traditional opera [11][12][13]. However, the comparative studies on Chinese and Japanese traditional opera tunes are relatively few and lack systematism and depth [14].Furthermore, China and Japan have deep historical and cultural origins, and there are many similarities in the traditional opera art between the two countries [15][16][17]. However, due to differences in language, region, and other aspects, there are also obvious differences between Chinese and Japanese traditional operas regarding tunes, performance, and costumes [18]. This difference is reflected in the form of performance on the surface, cultural connotation, and artistic value [19][20][21]. A comparative study of Chinese and Japanese traditional opera tunes can help to better understand the d...

show abstract

New objective timbre parameters for classification of voice type and fach in professional opera singers

Cited by 4 publications

References 17 publications

Harnessing Machine Learning in Vocal Arts Medicine: A Random Forest Application for “Fach” Classification in Opera

Harnessing Machine Learning in Vocal Arts Medicine: A Random Forest Application for “Fach” Classification in Opera

Experienced Listeners’ Perception of Timbre Dissimilarity Within and Between Voice Categories

The Analysis of Chinese and Japanese Traditional Opera Tunes With Artificial Intelligence Technology Based on Deep Learning

Contact Info

Product

Resources

About