Creating an A Cappella Singing Audio Dataset for Automatic Jingju Singing Evaluation Research

Gong, Rong; Repetto, Rafael Caro; Serra, Xavier

doi:10.1145/3144749.3144757

Cited by 4 publications

(4 citation statements)

References 2 publications

(2 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on that, Gong et al. [37] extend the dataset for some evaluation research, Repetto et al. [38] present a quantitative analysis of the relationship between linguistic tones and melody in Jingju, and Zhang et al.…”

Section: Related Workmentioning

confidence: 99%

“…Repetto et al [36] presented the first collection of machinereadable scores for the study of Jingju singing, including 92 scores covering 897 melodic lines accompanied by their metadata and curated annotations per score and melodic line. Based on that, Gong et al [37] extend the dataset for some evaluation research, Repetto et al [38] present a quantitative analysis of the relationship between linguistic tones and melody in Jingju, and Zhang et al [39] propose a novel approach to study the expressive functions of banshi (some rhythmic devices used in Jingju) by applying text analysis techniques on lyrics. In a word, there is some MIR-related research on representing and quantitatively evaluating certain types of Chinese music but few on technically interpreting the characteristics of Chinese music style.…”

Section: Chinese Music and Its Computationmentioning

confidence: 99%

See 1 more Smart Citation

Influence of musical elements on the perception of ‘Chinese style’ in music

Zhou

Sun

2022

Cognitive Comp and Systems

View full text Add to dashboard Cite

Recently Chinese music has been regarded as an independent music school. However, the definition of Chinese music has been an abstract and subjective concept. That makes music information retrieval (MIR) tasks hard to perform on Chinese music. Previous musicological studies have explained how musical elements like melody and instruments shape a certain kind of music genre including Chinese music, but the findings cannot be directly applied to relevant MIR tasks towards large‐scale users and real‐world problems. In this study, a pipeline of performing a perceptual survey is designed to explore how different musical elements influence people's perception of ‘Chinese style’ in music. Participants with various backgrounds were presented with categorised music excerpts performed in the Erhu or violin and then gave ‘Chinese style’ ratings. Statistical analysis indicates that music content contributes more than instruments. Results were compared between musicians and non‐musicians. Subsequently, a supplementary automatic music classification experiment is conducted in comparison with the survey results to discuss the authors’ choice of stimuli in the survey and similarities between computer auditory and human perception. In general, the results in this study can be useful for MIR tasks, such as understanding, representation, and recommendation of Chinese music.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Chinese Music and Its Computationmentioning

confidence: 99%

Influence of musical elements on the perception of ‘Chinese style’ in music

Zhou

Sun

2022

Cognitive Comp and Systems

View full text Add to dashboard Cite

show abstract

“…The second dataset we will use is a subset of the Jingju (Beijing Opera) A Capella Singing Audio Dataset [28,29]. It has been recorded in a teacher/student manner, collecting a capella recordings from professional singers and singing students, which permits to get pairs of recordings.…”

Section: Data Descriptionmentioning

confidence: 99%

On-Line Audio-to-Lyrics Alignment Based on a Reference Performance

Brazier,

Widmer

2021

Preprint

View full text Add to dashboard Cite

Audio-to-lyrics alignment has become an increasingly active research task in MIR, supported by the emergence of several open-source datasets of audio recordings with word-level lyrics annotations. However, there are still a number of open problems, such as a lack of robustness in the face of severe duration mismatches between audio and lyrics representation; a certain degree of language-specificity caused by acoustic differences across languages; and the fact that most successful methods in the field are not suited to work in real-time. Real-time lyrics alignment (tracking) would have many useful applications, such as fully automated subtitle display in live concerts and opera. In this work, we describe the first real-timecapable audio-to-lyrics alignment pipeline that is able to robustly track the lyrics of different languages, without additional language information. The proposed model predicts, for each audio frame, a probability vector over (European) phoneme classes, using a very small temporal context, and aligns this vector with a phoneme posteriogram matrix computed beforehand from another recording of the same work, which serves as a reference and a proxy to the written-out lyrics. We evaluate our system's tracking accuracy on the challenging genre of classical opera. Finally, robustness to out-of-training languages is demonstrated in an experiment on Jingju (Beijing opera).

show abstract

“…One of the most extensive databases for computational ethnomusicology has been collected within the CompMusic research project (Serra, 2014b). The collection comprises recordings of Indian Art music (Carnatic and Hindustani music) (Srinivasamurthy et al, 2014), Turkish Makam (Uyar et al, 2014Dzhambazov et al, 2016;Şentürk, 2016), Jingju (Repetto and Serra, 2014;Gong et al, 2017), and Andalusian music (Repetto et al, 2018). The individual corpora, which include annotations of lyrics, scores, and editorial metadata, are hosted on the webplatform Dunya.…”

Section: Related Datasets and Toolsmentioning

confidence: 99%

Erkomaishvili Dataset: A Curated Corpus of Traditional Georgian Vocal Music for Computational Musicology

Rosenzweig¹,

Scherbaum²,

Shugliashvili³

et al. 2020

Transactions of the International Society for Music Information Retrieval

View full text Add to dashboard Cite

The analysis of recorded audio material using computational methods has received increased attention in ethnomusicological research. We present a curated dataset of traditional Georgian vocal music for computational musicology. The corpus is based on historic tape recordings of three-voice Georgian songs performed by the the former master chanter Artem Erkomaishvili. In this article, we give a detailed overview of the audio material, transcriptions, and annotations contained in the dataset. Beyond its importance for ethnomusicological research, this carefully organized and annotated corpus constitutes a challenging scenario for music information retrieval tasks such as fundamental frequency estimation, onset detection, and score-to-audio alignment. The corpus is publicly available and accessible through score-following web-players.

show abstract

Creating an A Cappella Singing Audio Dataset for Automatic Jingju Singing Evaluation Research

Cited by 4 publications

References 2 publications

Influence of musical elements on the perception of ‘Chinese style’ in music

Influence of musical elements on the perception of ‘Chinese style’ in music

On-Line Audio-to-Lyrics Alignment Based on a Reference Performance

Erkomaishvili Dataset: A Curated Corpus of Traditional Georgian Vocal Music for Computational Musicology

Contact Info

Product

Resources

About