Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2411.12641

Improving Controllability and Editability for Pretrained Text-to-Music Generation Models

Yixiao Zhang
View original source ↗Read source document ↗Export metadata ↓

Abstract

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 generated content and allowing for flexible, precise edits. This thesis tackles these issues by introducing a series of advancements that progressively build upon each other, enhancing the controllability and editability of text-to-music generation models. First, we introduce Loop Copilot, a system that tries to address the need for iterative refinement in music creation. Loop Copilot leverages a large language model (LLM) to coordinate multiple specialised AI models, enabling users to generate and refine music interactively through a conversational interface. Central to this system is the Global Attribute Table, which records and maintains key musical attributes throughout the iterative process, ensuring that modifications at any stage preserve the overall coherence of the music. While Loop Copilot excels in orchestrating the music creation process, it does not directly address the need for detailed edits to the generated content. To overcome this limitation, MusicMagus is presented as a further solution for editing AI-generated music. MusicMagus introduces a zero-shot text-to-music editing approach that allows for the modification of specific musical attributes, such as genre, mood, and instrumentation, without the need for retraining. By manipulating the latent space within pre-trained diffusion models, MusicMagus ensures that these edits are stylistically coherent and that non-targeted attributes remain unchanged. This system is particularly effective in maintaining the structural integrity of the music during edits, but it encounters challenges with more complex and real-world audio scenarios. ...

Explore related subjects

cs.SDeess.AS

Keep this discovery

BibTeXRIS

Yixiao Zhang. 2024-11-19. Improving Controllability and Editability for Pretrained Text-to-Music Generation Models. https://arxiv.org/abs/2411.12641

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Xiaomi-CocktailASR-1 Technical Report

Recently, large language model (LLM) based ASR models have achieved significant progress, yet they generally lack support for multi-speaker scenarios, where the cocktail party problem remains a critical bottleneck for further advancing ASR. Existing TS-ASR methods, including end-to-end architectures with speaker embeddings and latest LLM-based explorations suffer from degraded single-speaker performance and the inability to reject when the target speaker is absent. In this paper, we propose Xiaomi-CocktailASR-1, an LLM-based end-to-end TS-ASR architecture. By utilizing reference speech as voiceprint prompts, it directly transcribes the target speaker's speech without requiring speech separation. Xiaomi-CocktailASR-1 maintains competitive performance in single-speaker scenarios, comparable to mainstream ASR models. It also features a negative sample rejection capability, outputting empty text when the target speaker is absent from the mixed speech. Additionally, Xiaomi-CocktailASR-1 supports a Chain-of-Thought (CoT) reasoning mode to provide explicit reasoning steps. Extensive experiments on various synthetic and real-world multispeaker benchmarks demonstrate that Xiaomi-CocktailASR-1 achieves state-of-the-art performance, effectively addressing the cocktail party problem through a unified architecture that balances multispeaker and single-speaker recognition accuracy, along with rejection capability.

cs.SD↗
arXiv2026

EConv-TasNet: Efficient Conv-TasNet for Effective Speech Separation

Conv-TasNet has served as a strong baseline for time-domain speech separation, and many studies have extended it with advanced architectures such as dual-path networks, U-Nets, and attention mechanisms. However, these methods often introduce high computational cost and complexity, limiting their deployment in resource-constrained scenarios. To address this issue, we propose eConv-TasNet, an efficient variant of Conv-TasNet that improves both effectiveness and efficiency without relying on resource-intensive modules. The proposed model consists of a group-wise early-splitting (GES) module and a multi-group feature aggregation (MGFA) module. GES generates discriminative speaker embeddings at intermediate stages, while MGFA progressively aggregates these group-level representations for refined mask estimation. Experimental results show that eConv-TasNet reduces model size by 22.4%, accelerates inference by 18.9%, and improves SI-SNRi by 14.0%-28.0% across three public benchmarks. Moreover, it achieves competitive performance compared with state-of-the-art methods while requiring significantly fewer parameters and lower inference cost. These results demonstrate a favorable efficiency-effectiveness trade-off for edge deployment.

cs.SD↗