paper-conference

DeepDrake ft. BTS-GAN and TayloRVC: An Exploratory Analysis of Musical Deepfakes and Hosting Platforms
Recent advancements in voice conversion and text-to-speech technology have facilitated the creation of musical deepfakes, audio tracks …
Michael Feffer, Zachary C. Lipton, Chris Donahue
PDF BibTeX Dataset
Melody Transcription via Generative Pre-training
Despite the central role that melody plays in music perception, it remains an open challenge in music information retrieval to reliably …
Chris Donahue, John Thickstun, Percy Liang
arXiv PDF BibTeX 🔊 Examples Code Dataset Video
It's Raw! Audio Generation with State-Space Models
Developing architectures suitable for modeling raw audio is a challenging problem due to the high sampling rates of audio waveforms. …
Karan Goel, Albert Gu, Chris Donahue, Christopher Ré
arXiv PDF BibTeX 🔊 Examples Code
Codified Audio Language Modeling Learns Useful Representations for Music Information Retrieval
We demonstrate that language models pre-trained on codified (discretely-encoded) music audio learn representations that are useful for …
Rodrigo Castellon, Chris Donahue, Percy Liang
arXiv PDF BibTeX Code
Towards Automatic Instrumentation by Learning to Separate Parts in Symbolic Multitrack Music
Modern keyboards allow a musician to play multiple instruments at the same time by assigning zones – fixed pitch ranges of the …
Hao-Wen Dong, Chris Donahue, Taylor Berg-Kirkpatrick, Julian McAuley
arXiv PDF BibTeX 🔊 Examples Code
Swords ⚔️: A Benchmark for Lexical Substitution with Improved Data Coverage and Quality
We release a new benchmark for lexical substitution, the task of finding appropriate substitutes for a target word in a context. To …
Mina Lee, Chris Donahue, Robin Jia, Alexander Iyabor, Percy Liang
arXiv PDF BibTeX Code Dataset
Enabling Language Models to Fill in the Blanks
We present a simple approach for text infilling, the task of predicting missing spans of text at any position in a document. While …
Chris Donahue, Mina Lee, Percy Liang
arXiv PDF BibTeX Code Demo
LakhNES: Improving Multi-instrumental Music Generation with Cross-domain Pre-training
We are interested in the task of generating multi-instrumental music scores. The Transformer architecture has recently shown great …
Chris Donahue, Huanru Henry Mao, Yiting Ethan Li, Garrison W. Cottrell, Julian McAuley
arXiv PDF BibTeX 🔊 Examples Code
Expediting TTS Synthesis with Adversarial Vocoding
Recent approaches in text-to-speech (TTS) synthesis employ neural network strategies to vocode perceptually-informed spectrogram …
Paarth Neekhara, Chris Donahue, Miller Puckette, Shlomo Dubnov, Julian McAuley
arXiv PDF BibTeX 🔊 Examples Code
Adversarial Audio Synthesis
Audio signals are sampled at high temporal resolutions, and learning to synthesize audio requires capturing structure across a range of …
Chris Donahue, Julian McAuley, Miller Puckette
arXiv PDF BibTeX 🔊 Examples Code 🕹️ Demo Notebook