Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2509.00914

TinyMusician: On-Device Music Generation with Knowledge Distillation and Mixed Precision Quantization

Hainan Wang·Mehdi Hosseinzadeh·Reza Rawassizadeh
View original source ↗Read source document ↗Export metadata ↓

Abstract

The success of the generative model has gained unprecedented attention in the music generation area. Transformer-based architectures have set new benchmarks for model performance. However, their practical adoption is hindered by some critical challenges: the demand for massive computational resources and inference time, due to their large number of parameters. These obstacles make them infeasible to deploy on edge devices, such as smartphones and wearables, with limited computational resources. In this work, we present TinyMusician, a lightweight music generation model distilled from MusicGen (a State-of-the-art music generation model). TinyMusician integrates two innovations: (i) Stage-mixed Bidirectional and Skewed KL-Divergence and (ii) Adaptive Mixed-Precision Quantization. The experimental results demonstrate that TinyMusician retains 93% of the MusicGen-Small performance with 55% less model size. TinyMusician is the first mobile-deployable music generation model that eliminates cloud dependency while maintaining high audio fidelity and efficient resource usage

Explore related subjects

cs.SDcs.AIeess.AS

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Hainan Wang, Mehdi Hosseinzadeh, Reza Rawassizadeh. 2025-08-31. TinyMusician: On-Device Music Generation with Knowledge Distillation and Mixed Precision Quantization. https://arxiv.org/abs/2509.00914

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↗