MGM-Omni: Scaling Omni LLMs to Personalized Long-Horizon Speech

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Chengyao, Zhong, Zhisheng, Peng, Bohao, Yang, Senqiao, Liu, Yuqi, Gui, Haokun, Xia, Bin, Li, Jingyao, Yu, Bei, Jia, Jiaya
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911183893692416
author Wang, Chengyao
Zhong, Zhisheng
Peng, Bohao
Yang, Senqiao
Liu, Yuqi
Gui, Haokun
Xia, Bin
Li, Jingyao
Yu, Bei
Jia, Jiaya
author_facet Wang, Chengyao
Zhong, Zhisheng
Peng, Bohao
Yang, Senqiao
Liu, Yuqi
Gui, Haokun
Xia, Bin
Li, Jingyao
Yu, Bei
Jia, Jiaya
contents We present MGM-Omni, a unified Omni LLM for omni-modal understanding and expressive, long-horizon speech generation. Unlike cascaded pipelines that isolate speech synthesis, MGM-Omni adopts a "brain-mouth" design with a dual-track, token-based architecture that cleanly decouples multimodal reasoning from real-time speech generation. This design enables efficient cross-modal interaction and low-latency, streaming speech generation. For understanding, a unified training strategy coupled with a dual audio encoder design enables long-form audio perception across diverse acoustic conditions. For generation, a chunk-based parallel decoding scheme narrows the text speech token-rate gap, accelerating inference and supporting streaming zero-shot voice cloning with stable timbre over extended durations. Compared to concurrent work, MGM-Omni achieves these capabilities with markedly data-efficient training. Extensive experiments demonstrate that MGM-Omni outperforms existing open source models in preserving timbre identity across extended sequences, producing natural and context-aware speech, and achieving superior long-form audio and omnimodal understanding. MGM-Omni establishes an efficient, end-to-end paradigm for omnimodal understanding and controllable, personalised long-horizon speech generation.
format Preprint
id arxiv_https___arxiv_org_abs_2509_25131
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MGM-Omni: Scaling Omni LLMs to Personalized Long-Horizon Speech
Wang, Chengyao
Zhong, Zhisheng
Peng, Bohao
Yang, Senqiao
Liu, Yuqi
Gui, Haokun
Xia, Bin
Li, Jingyao
Yu, Bei
Jia, Jiaya
Sound
Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
Multimedia
We present MGM-Omni, a unified Omni LLM for omni-modal understanding and expressive, long-horizon speech generation. Unlike cascaded pipelines that isolate speech synthesis, MGM-Omni adopts a "brain-mouth" design with a dual-track, token-based architecture that cleanly decouples multimodal reasoning from real-time speech generation. This design enables efficient cross-modal interaction and low-latency, streaming speech generation. For understanding, a unified training strategy coupled with a dual audio encoder design enables long-form audio perception across diverse acoustic conditions. For generation, a chunk-based parallel decoding scheme narrows the text speech token-rate gap, accelerating inference and supporting streaming zero-shot voice cloning with stable timbre over extended durations. Compared to concurrent work, MGM-Omni achieves these capabilities with markedly data-efficient training. Extensive experiments demonstrate that MGM-Omni outperforms existing open source models in preserving timbre identity across extended sequences, producing natural and context-aware speech, and achieving superior long-form audio and omnimodal understanding. MGM-Omni establishes an efficient, end-to-end paradigm for omnimodal understanding and controllable, personalised long-horizon speech generation.
title MGM-Omni: Scaling Omni LLMs to Personalized Long-Horizon Speech
topic Sound
Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
Multimedia
url https://arxiv.org/abs/2509.25131