The Experts below are selected from a list of 360 Experts worldwide ranked by ideXlab platform
Yihsuan Yang - One of the best experts on this subject based on the ideXlab platform.
-
Pop Music transformer generating Music with rhythm and harmony
2020Co-Authors: Yusiang Huang, Yihsuan YangAbstract:A great number of deep learning based models have been recently proposed for automatic Music composition. Among these models, the Transformer stands out as a prominent approach for generating expressive classical piano performance with a coherent structure of up to one minute. The model is powerful in that it learns abstractions of data on its own, without much human-imposed domain knowledge or constraints. In contrast with this general approach, this paper shows that Transformers can do even better for Music modeling, when we improve the way a Musical score is converted into the data fed to a Transformer model. In particular, we seek to impose a metrical structure in the input data, so that Transformers can be more easily aware of the beat-bar-phrase hierarchical structure in Music. The new data representation maintains the flexibility of local tempo changes, and provides hurdles to control the rhythmic and harmonic structure of Music. With this approach, we build a Pop Music Transformer that composes Pop piano Music with better rhythmic structure than existing Transformer models.
-
Pop Music transformer beat based modeling and generation of expressive Pop piano compositions
arXiv: Sound, 2020Co-Authors: Yusiang Huang, Yihsuan YangAbstract:A great number of deep learning based models have been recently proposed for automatic Music composition. Among these models, the Transformer stands out as a prominent approach for generating expressive classical piano performance with a coherent structure of up to one minute. The model is powerful in that it learns abstractions of data on its own, without much human-imposed domain knowledge or constraints. In contrast with this general approach, this paper shows that Transformers can do even better for Music modeling, when we improve the way a Musical score is converted into the data fed to a Transformer model. In particular, we seek to impose a metrical structure in the input data, so that Transformers can be more easily aware of the beat-bar-phrase hierarchical structure in Music. The new data representation maintains the flexibility of local tempo changes, and provides hurdles to control the rhythmic and harmonic structure of Music. With this approach, we build a Pop Music Transformer that composes Pop piano Music with better rhythmic structure than existing Transformer models.
-
Pop Music highlighter marking the emotion keypoints
arXiv: Audio and Speech Processing, 2018Co-Authors: Yusiang Huang, Szuyu Chou, Yihsuan YangAbstract:The goal of Music highlight extraction, or thumbnailing, is to extract a short consecutive segment of a piece of Music that is somehow representative of the whole piece. In a previous work, we introduced an attention-based convolutional recurrent neural network that uses Music emotion classification as a surrogate task for Music highlight extraction, assuming that the most emotional part of a song usually corresponds to the highlight. This paper extends our previous work in the following two aspects. First, methodology-wise we experiment with a new architecture that does not need any recurrent layers, making the training process faster. Moreover, we compare a late-fusion variant and an early-fusion variant to study which one better exploits the attention mechanism. Second, we conduct and report an extensive set of experiments comparing the proposed attention-based methods to a heuristic energy-based method, a structural repetition-based method, and three other simple feature-based methods, respectively. Due to the lack of public-domain labeled data for highlight extraction, following our previous work we use the RWC-Pop 100-song data set to evaluate how the detected highlights overlap with any chorus sections of the songs. The experiments demonstrate superior effectiveness of our methods over the competing methods. For reproducibility, we share the code and the pre-trained model at https://github.com/remyhuang/Pop-Music-highlighter/ .
-
Pop Music highlighter marking the emotion keypoints
arXiv: Audio and Speech Processing, 2018Co-Authors: Yusiang Huang, Szuyu Chou, Yihsuan YangAbstract:The goal of Music highlight extraction is to get a short consecutive segment of a piece of Music that provides an effective representation of the whole piece. In a previous work, we introduced an attention-based convolutional recurrent neural network that uses Music emotion classification as a surrogate task for Music highlight extraction, for Pop songs. The rationale behind that approach is that the highlight of a song is usually the most emotional part. This paper extends our previous work in the following two aspects. First, methodology-wise we experiment with a new architecture that does not need any recurrent layers, making the training process faster. Moreover, we compare a late-fusion variant and an early-fusion variant to study which one better exploits the attention mechanism. Second, we conduct and report an extensive set of experiments comparing the proposed attention-based methods against a heuristic energy-based method, a structural repetition-based method, and a few other simple feature-based methods for this task. Due to the lack of public-domain labeled data for highlight extraction, following our previous work we use the RWC Pop 100-song data set to evaluate how the detected highlights overlap with any chorus sections of the songs. The experiments demonstrate the effectiveness of our methods over competing methods. For reproducibility, we open source the code and pre-trained model at this https URL
-
the mood of chinese Pop Music representation and recognition
Association for Information Science and Technology, 2017Co-Authors: Yihsuan YangAbstract:Music mood recognition MMR has attracted much attention in Music information retrieval research, yet there are few MMR studies that focus on non-Western Music. In addition, little has been done on connecting the 2 most adopted Music mood representation models: categorical and dimensional. To bridge these gaps, we constructed a new data set consisting of 818 Chinese Pop C-Pop songs, 3 complete sets of mood annotations in both representations, as well as audio features corresponding to 5 distinct categories of Musical characteristics. The mood space of C-Pop songs was analyzed and compared to that of Western Pop songs. We also explored the relationship between categorical and dimensional annotations and the results revealed that one set of annotations could be reliably predicted by the other. Classification and regression experiments were conducted on the data set, providing benchmarks for future research on MMR of non-Western Music. Based on these analyses, we reflect and discuss the implications of the findings to MMR research.
Bob Stanley - One of the best experts on this subject based on the ideXlab platform.
-
yeah yeah yeah the story of Pop Music from bill haley to beyonce
2014Co-Authors: Bob StanleyAbstract:As much fun to argue with as to quote, Yeah! Yeah! Yeah! is a monumental work of Musical history, tracing the story of Pop Music through individual songs, bands, Musical scenes, and styles from Bill Haley and the Comets' "Rock around the Clock" (1954) to Beyonce's first megahit, "Crazy in Love" (2003). It covers the birth of rock, soul, RB explores what connects doo wop to the sock hop; and reveals how technological changes have affected Pop production. Working with a broad definition of "Pop"-one that includes country and metal, disco and Dylan, skiffle and glam-Stanley teases out the connections and tensions that animate the Pop charts and argues that the charts are vital social history. Yeah! Yeah! Yeah! is like the world's best and most eclectic jukebox in book form. All the hits are here: the Monkees, Metallica, Patsy Cline, Patti Smith, new wave, New Order, "It's the Same Old Song," The Song Remains the Same, Aretha, Bowie, Madonna, Prince, Sgt. Pepper, A Tribe Called Quest, the Big Bopper, Fleetwood Mac, "Itsy Bitsy Teenie Weenie Yellow Polka Dot Bikini," Bikini Kill, the Kinks, Mick Jagger, Michael Jackson, Jay-Z, and on and on and on. This book will have you reaching for your records (or CDs or MP3s) and discovering countless others. For anyone who has ever thrilled to the opening chord of the Beatles' "A Hard Day's Night" or fallen crazy in love for Beyonce, Yeah! Yeah! Yeah! is a vital guide to the rich soundtrack of the second half of the twentieth century.
Jorg Matthes - One of the best experts on this subject based on the ideXlab platform.
-
sexually objectifying Pop Music videos young women s self objectification and selective exposure a moderated mediation model
Communication Research, 2020Co-Authors: Kathrin Karsay, Jorg MatthesAbstract:There is intense discussion among experts about the potential negative impact of sexually objectifying media content on young women. This article presents an experimental study in which young women were either exposed to Pop Music videos high in sexual objectification or to Pop Music videos low in sexual objectification. Women’s self-objectification and their subsequent media selection behavior were measured. The results indicate that exposure to sexually objectifying media increased self-objectification, which in turn increased the preference for objectifying media content. Self-esteem, the internalization of appearance ideals, and body mass index (BMI) did not influence these relationships. Implications of these findings are discussed.
Wangkong Lam - One of the best experts on this subject based on the ideXlab platform.
-
similarity measures for chinese Pop Music based on low level audio signal attributes
International Symposium Conference on Music Information Retrieval, 2010Co-Authors: Chunman Mak, Tan Lee, Suman Senapati, Yu Ting Yeung, Wangkong LamAbstract:In this article a method of computing similarity of two Chinese Pop songs is presented. It is based on five attributes extracted from the audio signal. They include Music instrument, singing voice style, singer gender, tempo, and degree of noisiness. We compare the computed similarity measures with similarity scores obtained with subjective listening by over 200 human subjects. The results show that rhythm and mood related attributes like tempo and degree of noisiness are most correlated to human perception of Chinese Pop songs. Instrument and singing style are relatively less relevant. The results of subjective evaluation also indicate that the proposed method of similarity computation is fairly correlated with human perception.
Karl Hagstrom Miller - One of the best experts on this subject based on the ideXlab platform.
-
segregating sound inventing folk and Pop Music in the age of jim crow
2010Co-Authors: Karl Hagstrom MillerAbstract:In Segregating Sound , Karl Hagstrom Miller argues that the categories that we have inherited to think and talk about southern Music bear little relation to the ways that southerners long played and heard Music. Focusing on the late nineteenth century and the early twentieth, Miller chronicles how southern Music—a fluid complex of sounds and styles in practice—was reduced to a series of distinct genres linked to particular racial and ethnic identities. The blues were African American. Rural white southerners played country Music. By the 1920s, these depictions were touted in folk song collections and the catalogs of “race” and “hillbilly” records produced by the phonograph industry. Such links among race, region, and Music were new. Black and white artists alike had played not only blues, ballads, ragtime, and string band Music, but also nationally Popular sentimental ballads, minstrel songs, Tin Pan Alley tunes, and Broadway hits. In a cultural history filled with Musicians, listeners, scholars, and business people, Miller describes how folklore studies and the Music industry helped to create a “Musical color line,” a cultural parallel to the physical color line that came to define the Jim Crow South. Segregated sound emerged slowly through the interactions of southern and northern Musicians, record companies that sought to penetrate new markets across the South and the globe, and academic folklorists who attempted to tap southern Music for evidence about the history of human civilization. Contending that people’s Musical worlds were defined less by who they were than by the Music that they heard, Miller challenges assumptions about the relation of race, Music, and the market.