By Paarth Neekhara, Shehzeen Hussain, Shlomo Dubnov, Farinaz Koushanfar, Julian McAuley Sat, 30 Jan 2021 Read full publication Abstract: Voice cloning is the task of learning to synthesize the voice of an unseen speaker from a few samples. While current voice cloning methods achieve promising results in Text-to-Speech (TTS) synthesis for a new voice, these […]
Dubnov, S. Predictive Quantization and Symbolic Dynamics. Algorithms 2022, 15, 484. https://doi.org/10.3390/a15120484 Read full article Abstract: Capturing long-term statistics of signals and time series is important for modeling recurrent phenomena, especially when such recurrences are a-periodic and can be characterized by the approximate repetition of variable length motifs, such as patterns in human gestures and trends in […]
By Vignesh Gokul. Computer Science [cs]. University of California San Diego, 2024. English. Read full publication. Abstract: With the development of intelligent chatbots, humans have found a method to communicate with artificial digital assistants. However, human beings are able to communicate an enormous amount of information without ever saying a word, eg gestures and music. […]
By Hao-Wen Dong. Sound [cs.SD]. University of California San Diego, 2024. English. Read full publication. Abstract: Generative AI has been transforming the way we interact with technology and consume content. In the next decade, AI technology will reshape how we create audio content in various media, including music, theater, films, games, podcasts, and short videos. […]
BySabina Covarrubias Stms. Journées d’informatique musicale, Micael Antunes; Jonathan Bell; Javier Elipe Gimeno; Mylène Gioffredo; Charles de Paiva Santana; Vincent Tiffon, May 2024, Marseille, France. Read full publication. Abstract: Improvisio is a software for musicians who want to improvise visual music. Its development is part of the REACH project. It is useful to create visual […]
Article by Marco Fiorini (STMS – IRCAM, Sorbonne Université, CNRS) has been accepted for the 13th EAI International Conference: ArtsIT, Interactivity & Game Creation at New York University in Abu Dhabi, United Arab Emirates Read the full paper Abstract: This essay explores the use of generative AI systems in cocreativity within musical improvisation, offering best practices for […]
Ke Chen, Xingjian Du, Bilei Zhu, Zejun Ma, Taylor Berg-Kirkpatrick, Shlomo Dubnov Proceedings of the AAAI Conference on Artificial Intelligence, 2022, Remote Conference, France. pp.4441-4449. Read full publication. Abstract: Deep learning techniques for separating audio into different sound sources face several challenges. Standard architectures require training separate models for different types of audio sources. Although […]
By Qiuqiang Kong, Ke Chen, Haohe Liu, Xingjian Du, Taylor Berg-Kirkpatrick,Shlomo Dubnov, Mark D Plumbley. Read full publication. Abstract: Universal source separation (USS) is a fundamental research task for computational auditory scene analysis, which aims to separate mono recordings into individual source tracks. There are three potential challenges awaiting the solution to the audio source […]
By Weihan Xu, Julian McAuley, Taylor Berg-Kirkpatrick, Shlomo Dubnov,Hao-Wen Dong ISMIR Late-Breaking Demos, Nov 2024, San Francisco, United States Read full publication. Abstract: Recent years have seen many audio-domain text-to-music generation models that rely on large amounts of text-audio pairs for training. However, similar attempts for symbolic-domain controllable music generation has been hindered due to […]
Ke Chen, Xingjian Du, Bilei Zhu, Zejun Ma, Taylor Berg-Kirkpatrick, Shlomo Dubnov ICASSP 2022 – 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2022, Singapore, France. pp.646-650 Read full publication. Abstract: Audio classification is an important task of mapping audio samples into their corresponding labels. Recently, the transformer model with self-attention […]