The Experts below are selected from a list of 10287 Experts worldwide ranked by ideXlab platform
George Tzanetakis - One of the best experts on this subject based on the ideXlab platform.
-
Musical genre classification of audio signals
IEEE Transactions on Speech and Audio Processing, 2002Co-Authors: George Tzanetakis, Perry CookAbstract:Musical genres are categorical labels created by humans to characterize pieces of music. A musical genre is characterized by the common characteristics shared by its members. These characteristics typically are related to the instrumentation, Rhythmic Structure, and harmonic content of the music. Genre hierarchies are commonly used to Structure the large collections of music available on the Web. Currently musical genre annotation is performed manually. Automatic musical genre classification can assist or replace the human user in this process and would be a valuable addition to music information retrieval systems. In addition, automatic musical genre classification provides a framework for developing and evaluating features for any type of content-based analysis of musical signals. In this paper, the automatic classification of audio signals into an hierarchy of musical genres is explored. More specifically, three feature sets for representing timbral texture, Rhythmic content and pitch content are proposed. The performance and relative importance of the proposed features is investigated by training statistical pattern recognition classifiers using real-world audio collections. Both whole file and real-time frame-based classification schemes are described. Using the proposed feature sets, classification of 61% for ten musical genres is achieved. This result is comparable to results reported for human musical genre classification.
-
automatic musical genre classification of audio signals
International Symposium Conference on Music Information Retrieval, 2001Co-Authors: George TzanetakisAbstract:Musical genres are categorical descriptions that are used to describe music. They are commonly used to Structure the increasing amounts of music available in digital form on the Web and are important for music information retrieval. Genre categorization for audio has traditionally been performed manually. A particular musical genre is characterized by statistical properties related to the instrumentation, Rhythmic Structure and form of its members. In this work, algorithms for the automatic genre categorization of audio signals are described. More specifically, we propose a set of features for representing texture and instrumentation. In addition a novel set of features for representing Rhythmic Structure and strength is proposed. The performance of those feature sets has been evaluated by training statistical pattern recognition classifiers using real world audio collections. Based on the automatic hierarchical genre classification two graphical user interfaces for browsing and interacting with large audio collections have been developed.
Perry Cook - One of the best experts on this subject based on the ideXlab platform.
-
Musical genre classification of audio signals
IEEE Transactions on Speech and Audio Processing, 2002Co-Authors: George Tzanetakis, Perry CookAbstract:Musical genres are categorical labels created by humans to characterize pieces of music. A musical genre is characterized by the common characteristics shared by its members. These characteristics typically are related to the instrumentation, Rhythmic Structure, and harmonic content of the music. Genre hierarchies are commonly used to Structure the large collections of music available on the Web. Currently musical genre annotation is performed manually. Automatic musical genre classification can assist or replace the human user in this process and would be a valuable addition to music information retrieval systems. In addition, automatic musical genre classification provides a framework for developing and evaluating features for any type of content-based analysis of musical signals. In this paper, the automatic classification of audio signals into an hierarchy of musical genres is explored. More specifically, three feature sets for representing timbral texture, Rhythmic content and pitch content are proposed. The performance and relative importance of the proposed features is investigated by training statistical pattern recognition classifiers using real-world audio collections. Both whole file and real-time frame-based classification schemes are described. Using the proposed feature sets, classification of 61% for ten musical genres is achieved. This result is comparable to results reported for human musical genre classification.
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.
Jonas Obleser - One of the best experts on this subject based on the ideXlab platform.
-
neural microstates govern perception of auditory input without Rhythmic Structure
The Journal of Neuroscience, 2016Co-Authors: Molly J Henry, Bjorn Herrmann, Jonas ObleserAbstract:Human perception fluctuates with the phase of neural oscillations in the presence of environmental Rhythmic Structure by which neural oscillations become entrained. However, in the absence of predictability afforded by Rhythmic Structure, we hypothesize that the neural dynamical states associated with optimal psychophysical performance are more complex than what has been described previously for Rhythmic stimuli. The current electroencephalography study characterized the brain dynamics associated with optimal detection of gaps embedded in narrow-band acoustic noise stimuli lacking low-frequency Rhythmic Structure. Optimal gap detection was associated with three spectrotemporally distinct delta-governed neural microstates. Individual microstates were characterized by unique instantaneous combinations of neural phase in the delta, theta, and alpha frequency bands. Critically, gap detection was not predictable from local fluctuations in stimulus acoustics. The current results suggest that, in the absence of Rhythmic Structure to entrain neural oscillations, good performance hinges on complex neural states that vary from moment to moment. Significance statement: Our ability to hear faint sounds fluctuates together with slow brain activity that synchronizes with environmental rhythms. However, it is so far not known how brain activity at different time scales might interact to influence perception when there is no rhythm with which brain activity can synchronize. Here, we used electroencephalography to measure brain activity while participants listened for short silences that interrupted ongoing noise. We examined brain activity in three different frequency bands: delta, theta, and alpha. Participants' ability to detect gaps depended on different numbers of frequency bands--sometimes one, sometimes two, and sometimes three--at different times. Changes in the number of frequency bands that predict perception are a hallmark of a complex neural system.
-
entrained neural oscillations in multiple frequency bands comodulate behavior
Proceedings of the National Academy of Sciences of the United States of America, 2014Co-Authors: Molly J Henry, Bjorn Herrmann, Jonas ObleserAbstract:Our sensory environment is teeming with complex Rhythmic Structure, to which neural oscillations can become synchronized. Neural synchronization to environmental rhythms (entrainment) is hypothesized to shape human perception, as Rhythmic Structure acts to temporally organize cortical excitability. In the current human electroencephalography study, we investigated how behavior is influenced by neural oscillatory dynamics when the Rhythmic fluctuations in the sensory environment take on a naturalistic degree of complexity. Listeners detected near-threshold gaps in auditory stimuli that were simultaneously modulated in frequency (frequency modulation, 3.1 Hz) and amplitude (amplitude modulation, 5.075 Hz); modulation rates and types were chosen to mimic the complex Rhythmic Structure of natural speech. Neural oscillations were entrained by both the frequency modulation and amplitude modulation in the stimulation. Critically, listeners’ target-detection accuracy depended on the specific phase–phase relationship between entrained neural oscillations in both the 3.1-Hz and 5.075-Hz frequency bands, with the best performance occurring when the respective troughs in both neural oscillations coincided. Neural-phase effects were specific to the frequency bands entrained by the Rhythmic stimulation. Moreover, the degree of behavioral comodulation by neural phase in both frequency bands exceeded the degree of behavioral modulation by either frequency band alone. Our results elucidate how fluctuating excitability, within and across multiple entrained frequency bands, shapes the effective neural processing of environmental stimuli. More generally, the frequency-specific nature of behavioral comodulation effects suggests that environmental rhythms act to reduce the complexity of high-dimensional neural states.
Ksenia Vadimovna Abramova - One of the best experts on this subject based on the ideXlab platform.
-
Intertextual Connections in Nikolai Shchegolev’s Lyrical Poetry: Pasternak, Mayakovski, Futurists
'Ural Federal University', 2021Co-Authors: Ksenia Vadimovna AbramovaAbstract:This article analyses the poetics of Nikolai Shchegolev’s works from the point of view of the influence of the futuristic and avant-garde tradition on the artistic world of his works. The research aims to identify semantic (themes and motifs) and asemantic aspects (such as the Rhythmic Structure and construction peculiarities of stanzas and rhymes) of Shchegolev’s poems. These aspects resonate with such phenomena in the poems that were associated in émigré circles with the revolution and Soviet Russia’s art. There is a tendency in scholarly literature to consider the works of poets and writers of the “Eastern branch” of emigration as part of the development of nineteenth-century classical literature and as a continuation of the traditions of symbolism and Acmeism. This approach is often associated with the special position of Harbin, the Russian city in China, which has become a kind of symbol of the past, as life there was based on the model of pre-revolutionary Russia. Nevertheless, some scholars (A. A. Zabiyako, G. V. Efendiyeva, E. O. Kirillova, E. Yu. Kulikova) note the reflection and development of Harbin poets’ avant-garde experience. Nikolai Shchegolev’s works, including these aspects, remain insufficiently explored. In this work, referring to historical and literary and structural and semiotic approaches and the principles of intertextual and poetic analysis, the author turns to the study of themes, motifs, and images, as well as rhythm and strophic Structures in the poetry of Nikolai Shchegolev, which makes it possible to deepen and summarise ideas about the poetics of his works. When considering individual texts, the author concludes that some themes and motifs (such as urban themes, the images of a cinematograph and a mannequin which is coming back to life, and the associated theme of oscillation between the living and the dead), as well as experiments with rhythm, strophic division, and word coinage were accepted and understood by Shchegolev through the poetry of Vladimir Mayakovski, Boris Pasternak, and the futurists