paper-with-me

Papers

Efficient Parallel Audio Generation using Group Masked Language Modeling

2024-01-02 · Myeonghun Jeong, Minchan Kim, Joun Yeop Lee, Nam Soo Kim

We present a fast and high-quality codec language model for parallel audio generation. While SoundStorm, a state-of-the-art parallel audio generation model, accelerates inference speed compared to autoregressive models, it still suffers from slow inference due to iterative sampling. To resolve this problem, we propose Group-Masked Language Modeling~(G-MLM) and Group Iterative Parallel Decoding~(G-IPD) for efficient parallel audio generation. Both the training and sampling schemes enable the model to synthesize high-quality audio with a small number of iterations by effectively modeling the group-wise conditional dependencies. In addition, our model employs a cross-attention-based architecture to capture the speaker style of the prompt voice and improves computational efficiency. Experimental results demonstrate that our proposed model outperforms the baselines in prompt-based audio generation.

📄 PDF Abstract BibTeX arXiv:2401.01099

Code (0)

등록된 구현이 없습니다.

Tasks

Audio GenerationComputational EfficiencyLanguage ModelingLanguage ModellingMasked Language Modeling

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Whisfusion: Parallel ASR Decoding with Masked Diffusion

2025-08-09 · Taeyoun Kwon, Junhyuk Ahn, Taegeun Yun, Heeju Jwa 외 arxiv

Autoregressive (AR) encoder-decoder models dominate high-quality multilingual ASR, but their left-to-right decoders make inference latency scale with transcript length. A natural alternative, CTC-style non-autoregressive…

Cluster-Level Attention-Guided Parallel Decoding for Masked Diffusion Language Models

2026-05-28 · Heqiang Qi, Wei Huang, Mingyuan Bai, Xiangming Meng arxiv

Masked diffusion language models (MDLMs) enable parallel decoding by predicting all masked positions at each denoising step, yet existing training-free samplers usually decide which positions to commit at token-level gra…

DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation

2025-10-14 · Yakun Song, Xiaobin Zhuang, Jiawei Chen, Zhikang Niu 외 arxiv

Recent attempts to interleave autoregressive (AR) sketchers with diffusion-based refiners over continuous speech representations have shown promise, but they remain brittle under distribution shift and offer limited leve…

Masked Audio Generation using a Single Non-Autoregressive Transformer

2024-01-09 · Alon Ziv, Itai Gat, Gael Le Lan, Tal Remez 외

We introduce MAGNeT, a masked generative sequence modeling method that operates directly over several streams of audio tokens. Unlike prior work, MAGNeT is comprised of a single-stage, non-autoregressive transformer. Dur…

Audio Generation

Masked Generative Video-to-Audio Transformers with Enhanced Synchronicity

2024-07-15 · Santiago Pascual, Chunghsin Yeh, Ioannis Tsiamas, Joan Serrà

Video-to-audio (V2A) generation leverages visual-only video features to render plausible sounds that match the scene. Importantly, the generated sound onsets should match the visual actions that are aligned with them, ot…

Video-to-Sound Generation