相关论文: MCMChaos: Improvising Rap Music with MCMC Methods …

Rap, a prominent genre of vocal performance, remains underexplored in vocal generation. General vocal synthesis depends on precise note and duration inputs, requiring users to have related musical knowledge, which limits flexibility. In…

Recent Text-to-Speech (TTS) systems trained on reading or acted corpora have achieved near human-level naturalness. The diversity of human speech, however, often goes beyond the coverage of these corpora. We believe the ability to handle…

In complex and unknown processes, global models are initially generated over the entire experimental space but often fail to provide accurate predictions in local areas. A common approach is to use local models, which requires partitioning…

Diffusion models have shown promising results in cross-modal generation tasks, including text-to-image and text-to-audio generation. However, generating music, as a special type of audio, presents unique challenges due to limited…

In daily life, we encounter a variety of sounds, both desirable and undesirable, with limited control over their presence and volume. Our work introduces "Listen, Chat, and Remix" (LCR), a novel multimodal sound remixer that controls each…

Recent advances in text-to-music (TTM) generation have enabled controllable and expressive music creation using natural language prompts. However, the emotional fidelity of TTM systems remains largely underexplored compared to human…

In this paper, a text-to-rapping/singing system is introduced, which can be adapted to any speaker's voice. It utilizes a Tacotron-based multispeaker acoustic model trained on read-only speech data and which provides prosody control at the…

We introduce MusicFlow, a cascaded text-to-music generation model based on flow matching. Based on self-supervised representations to bridge between text descriptions and music audios, we construct two flow matching networks to model the…

Very short computer programs, sometimes consisting of as few as three arithmetic operations in an infinite loop, can generate data that sounds like music when output as raw PCM audio. The space of such programs was recently explored by…

Polynomial Chaos Expansions represent a powerful tool to simulate stochastic models of dynamical systems. Yet, deriving the expansion's coefficients for complex systems might require a significant and non-trivial manipulation of the model,…

The field of AI-assisted music creation has made significant strides, yet existing systems often struggle to meet the demands of iterative and nuanced music production. These challenges include providing sufficient control over the…

The background numerical noise $\varepsilon_{0} $ is determined by the maximum of truncation error and round-off error. For a chaotic system, the numerical error $\varepsilon(t)$ grows exponentially, say, $\varepsilon(t) = \varepsilon_{0}…

Language models (LMs) can generate code but cannot guarantee its correctness$\unicode{x2014}$often producing outputs that violate type safety, program invariants, or other semantic properties. Constrained decoding offers a solution by…

Text-to-speech (TTS) has advanced from generating natural-sounding speech to enabling fine-grained control over attributes like emotion, timbre, and style. Driven by rising industrial demand and breakthroughs in deep learning, e.g.,…

Generating images that fit a given text description using machine learning has improved greatly with the release of technologies such as the CLIP image-text encoder model; however, current methods lack artistic control of the style of image…

This paper introduces RyanSpeech, a new speech corpus for research on automated text-to-speech (TTS) systems. Publicly available TTS corpora are often noisy, recorded with multiple speakers, or lack quality male speech data. In order to…

Recently developed adaptive Markov chain Monte Carlo (MCMC) methods have been applied successfully to many problems in Bayesian statistics. Grapham is a new open source implementation covering several such methods, with emphasis on…

In this paper, we present ControlSpeech, a text-to-speech (TTS) system capable of fully cloning the speaker's voice and enabling arbitrary control and adjustment of speaking style. Prior zero-shot TTS models only mimic the speaker's voice…

Multimodal models excel in English, supported by abundant image-text and audio-text data, but performance drops sharply for other languages due to limited multilingual multimodal resources. Existing solutions rely on machine translation,…

Mellotron is a multispeaker voice synthesis model based on Tacotron 2 GST that can make a voice emote and sing without emotive or singing training data. By explicitly conditioning on rhythm and continuous pitch contours from an audio signal…