Long-form music generation with latent diffusion
Audio-based generative models for music have seen great strides recently, but so far have
not managed to produce full-length music tracks with coherent musical structure. We show …
not managed to produce full-length music tracks with coherent musical structure. We show …
Emo-DPO: Controllable Emotional Speech Synthesis through Direct Preference Optimization
Current emotional text-to-speech (TTS) models predominantly conduct supervised training
to learn the conversion from text and desired emotion to its emotional speech, focusing on a …
to learn the conversion from text and desired emotion to its emotional speech, focusing on a …
MusicScore: A Dataset for Music Score Modeling and Generation
Music scores are written representations of music and contain rich information about musical
components. The visual information on music scores includes notes, rests, staff lines, clefs …
components. The visual information on music scores includes notes, rests, staff lines, clefs …
Crafting Creative Melodies: A User-Centric Approach for Symbolic Music Generation
S Dadman, BA Bremdal - Electronics, 2024 - mdpi.com
Composing coherent and structured music is one of the main challenges in symbolic music
generation. Our research aims to propose a user-centric framework design that promotes a …
generation. Our research aims to propose a user-centric framework design that promotes a …
Enhancing Zero-shot Text-to-Speech Synthesis with Human Feedback
In recent years, text-to-speech (TTS) technology has witnessed impressive advancements,
particularly with large-scale training datasets, showcasing human-level speech quality and …
particularly with large-scale training datasets, showcasing human-level speech quality and …
MAD Speech: Measures of Acoustic Diversity of Speech
M Futeral, A Agostinelli, M Tagliasacchi… - arXiv preprint arXiv …, 2024 - arxiv.org
Generative spoken language models produce speech in a wide range of voices, prosody,
and recording conditions, seemingly approaching the diversity of natural speech. However …
and recording conditions, seemingly approaching the diversity of natural speech. However …
Seed-Music: A Unified Framework for High Quality and Controlled Music Generation
We introduce Seed-Music, a suite of music generation systems capable of producing high-
quality music with fine-grained style control. Our unified framework leverages both auto …
quality music with fine-grained style control. Our unified framework leverages both auto …
Bailing-TTS: Chinese Dialectal Speech Synthesis Towards Human-like Spontaneous Representation
X Di, Z Chen, Y Liang, J Zheng, Y Wang… - arXiv preprint arXiv …, 2024 - arxiv.org
Large-scale text-to-speech (TTS) models have made significant progress recently. However,
they still fall short in the generation of Chinese dialectal speech. Toaddress this, we propose …
they still fall short in the generation of Chinese dialectal speech. Toaddress this, we propose …
Dynamic Normativity: Necessary and Sufficient Conditions for Value Alignment
NK Corrêa - arXiv preprint arXiv:2406.11039, 2024 - arxiv.org
The critical inquiry pervading the realm of Philosophy, and perhaps extending its influence
across all Humanities disciplines, revolves around the intricacies of morality and normativity …
across all Humanities disciplines, revolves around the intricacies of morality and normativity …
Human-Machine Co-creation in an Electroacoustic Ensemble Performance Context
RD Hoy, D Van Nort - Proceedings of the 19th International Audio Mostly …, 2024 - dl.acm.org
This paper investigates the outcomes of incorporating computational agents into a telematic
electroacoustic performance ensemble. The ensemble is directed by a gestural language …
electroacoustic performance ensemble. The ensemble is directed by a gestural language …