Zobrazeno 1 - 10
of 31
pro vyhledávání: '"Gus Xia"'
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
The variational auto-encoder has become a leading framework for symbolic music generation, and a popular research direction is to study how to effectively control the generation process. A straightforward way is to control a model using different con
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b85cfc8599e308382a40f8010b85beba
We propose Beat Transformer, a novel Transformer encoder architecture for joint beat and downbeat tracking. Different from previous models that track beats solely based on the spectrogram of an audio mixture, our model deals with demixed spectrograms
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c47ea32f84e85effefc4ed3cdad060c0
http://arxiv.org/abs/2209.07140
http://arxiv.org/abs/2209.07140
Autor:
Yinghao Ma, Ruibin Yuan, Yizhi Li, Ge Zhang, Xingran Chen, Hanzhi Yin, Chenghua Lin, Benetos, Emmanouil, Ragni, Anton, Gyenge, Norbert, Ruibo Liu, Gus Xia, Dannenberg, Roger, Yike Guo, Jie Fu
Publikováno v:
International Society for Music Information Retrieval Conference Proceedings; 2023, p457-465, 9p
Publikováno v:
International Society for Music Information Retrieval Conference Proceedings; 2023, p231-238, 8p
Autor:
Daniel Chin, Gus Xia
Publikováno v:
NIME 2022.
BERT has proven to be a powerful language model in natural language processing and established an effective pre-training & fine-tuning methodology. We see that music, as a special form of language, can benefit from such methodology if we carefully ha
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::43a4f2469641cdba0cef6a23dc13a785
Publikováno v:
NIME 2021.
Haptic interfaces enhance the learning efficiency in music learning, but most existing studies focus on training motor skills of instrument playing such as finger motions. In this paper, we present a wearable haptic device to guide diaphragmatic brea
Publikováno v:
NIME 2021.
In this paper, we propose COSMIC, a COnverSational Interface for Human-AI MusIc Co-Creation. It is a chatbot with a two-fold design philosophy: to understand human creative intent and to help humans in their creation. The core Natural Language Proces
Autor:
Gus Xia, Yixiao Zhang
Publikováno v:
Proceedings of the 8th Conference on Sound and Music Technology ISBN: 9789811616488
Automatic melodic phrase detection and segmentation is a classical task of content-based music information retrieval and also a key problem of automatic music structure analysis. In this paper, we apply neural network architectures with conditional r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0a7eb4fb1ef94ec2adf2503c36a5bcb4
https://doi.org/10.1007/978-981-16-1649-5_5
https://doi.org/10.1007/978-981-16-1649-5_5