MoST: Mixing Speech and Text with Modality-Aware Mixture of Experts

• URL: http://arxiv.org/abs/2601.10272v1
• Date: Thu, 15 Jan 2026 10:43:29 GMT
• Title: MoST: Mixing Speech and Text with Modality-Aware Mixture of Experts
• Authors: Yuxuan Lou, Kai Yang, Yang You,
• Abstract summary: MoST (Mixture of Speech and Text) is a novel large language model that seamlessly integrates speech and text processing.<n>We introduce specialized routing pathways that direct tokens to modality-appropriate experts based on input type.<n>MoST consistently outperforms existing models of comparable parameter counts.
• Score: 12.42628977620548
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present MoST (Mixture of Speech and Text), a novel multimodal large language model that seamlessly integrates speech and text processing through our proposed Modality-Aware Mixture of Experts (MAMoE) architecture. While current multimodal models typically process diverse modality representations with identical parameters, disregarding their inherent representational differences, we introduce specialized routing pathways that direct tokens to modality-appropriate experts based on input type. MAMoE simultaneously enhances modality-specific learning and cross-modal understanding through two complementary components: modality-specific expert groups that capture domain-specific patterns and shared experts that facilitate information transfer between modalities. Building on this architecture, we develop an efficient transformation pipeline that adapts the pretrained MoE language model through strategic post-training on ASR and TTS datasets, followed by fine-tuning with a carefully curated speech-text instruction dataset. A key feature of this pipeline is that it relies exclusively on fully accessible, open-source datasets to achieve strong performance and data efficiency. Comprehensive evaluations across ASR, TTS, audio language modeling, and spoken question answering benchmarks show that MoST consistently outperforms existing models of comparable parameter counts. Our ablation studies confirm that the modality-specific routing mechanism and shared experts design significantly contribute to performance gains across all tested domains. To our knowledge, MoST represents the first fully open-source speech-text LLM built on a Mixture of Experts architecture. \footnote{We release MoST model, training code, inference code, and training data at https://github.com/NUS-HPC-AI-Lab/MoST

Related papers

• Wasm: A Pipeline for Constructing Structured Arabic Interleaved Multimodal Corpora [1.7590081165362783]
  We present our pipeline Wasm for processing the Common Crawl dataset to create a new Arabic multimodal dataset.<n>Unlike existing Arabic corpora that focus solely on text extraction, our approach preserves the structural integrity of web content.<n>We provide a comprehensive comparative analysis of our data processing pipeline against those used for major existing datasets.
  arXiv  Detail & Related papers  (2025-11-10T13:10:31Z)
• MoIIE: Mixture of Intra- and Inter-Modality Experts for Large Vision Language Models [52.876185634349575]
  We propose to incorporate Mixture of Intra- and Inter-Modality Experts (MoIIE) to Large Vision-Language Models (LVLMs)<n>For each token, expert routing is guided by its modality, directing tokens to their respective intra-modality experts as well as a shared pool of inter-modality experts.<n>Our MoIIE models with 5.5B and 11.3B activated parameters match or even surpass the performance of existing advanced open-source MoE-LLMs based multi-modal models.
  arXiv  Detail & Related papers  (2025-08-13T13:00:05Z)
• TAViS: Text-bridged Audio-Visual Segmentation with Foundation Models [123.17643568298116]
  We present TAViS, a novel framework that textbfcouples the knowledge of multimodal foundation models for cross-modal alignment.<n> effectively combining these models poses two key challenges: the difficulty in transferring the knowledge between SAM2 and ImageBind due to their different feature spaces, and the insufficiency of using only segmentation loss for supervision.<n>Our approach achieves superior performance on single-source, multi-source, semantic datasets, and excels in zero-shot settings.
  arXiv  Detail & Related papers  (2025-06-13T03:19:47Z)
• Zipper: A Multi-Tower Decoder Architecture for Fusing Modalities [6.9522425458326635]
  We propose a multi-tower decoder architecture that flexibly composes multimodal generative models from independently pre-trained unimodal decoders. We show the proposed architecture performs very competitively in scenarios with limited aligned text-speech data. In cross-modal tasks such as text-to-speech generation (TTS) where the output modality is speech, we show that using a pre-trained speech backbone results in superior performance to the baseline.
  arXiv  Detail & Related papers  (2024-05-29T00:23:55Z)
• Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts [54.529880848937104]
  We develop a unified MLLM with the MoE architecture, named Uni-MoE, that can handle a wide array of modalities. Specifically, it features modality-specific encoders with connectors for a unified multimodal representation. We evaluate the instruction-tuned Uni-MoE on a comprehensive set of multimodal datasets.
  arXiv  Detail & Related papers  (2024-05-18T12:16:01Z)
• Multi-modal Semantic Understanding with Contrastive Cross-modal Feature Alignment [11.897888221717245]
  This paper proposes a novel CLIP-guided contrastive-learning-based architecture to perform multi-modal feature alignment. Our model is simple to implement without using task-specific external knowledge, and thus can easily migrate to other multi-modal tasks.
  arXiv  Detail & Related papers  (2024-03-11T01:07:36Z)
• AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling [115.56746545958522]
  We introduce AnyGPT, an any-to-any multimodal language model that utilizes discrete representations for the unified processing of various modalities.<n>We build a multimodal text-centric dataset for multimodal alignment pre-training.<n>We show that AnyGPT is capable of facilitating any-to-any multimodal conversation while achieving performance comparable to specialized models across all modalities.
  arXiv  Detail & Related papers  (2024-02-19T15:33:10Z)
• FLIP: Fine-grained Alignment between ID-based Models and Pretrained Language Models for CTR Prediction [49.510163437116645]
  Click-through rate (CTR) prediction plays as a core function module in personalized online services. Traditional ID-based models for CTR prediction take as inputs the one-hot encoded ID features of tabular modality. Pretrained Language Models(PLMs) has given rise to another paradigm, which takes as inputs the sentences of textual modality. We propose to conduct Fine-grained feature-level ALignment between ID-based Models and Pretrained Language Models(FLIP) for CTR prediction.
  arXiv  Detail & Related papers  (2023-10-30T11:25:03Z)
• Cross-Modal Multi-Tasking for Speech-to-Text Translation via Hard Parameter Sharing [72.56219471145232]
  We propose a ST/MT multi-tasking framework with hard parameter sharing. Our method reduces the speech-text modality gap via a pre-processing stage. We show that our framework improves attentional encoder-decoder, Connectionist Temporal Classification (CTC), transducer, and joint CTC/attention models by an average of +0.5 BLEU.
  arXiv  Detail & Related papers  (2023-09-27T17:48:14Z)
• Leveraging Uni-Modal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition [23.239078852797817]
  We leverage uni-modal self-supervised learning to promote the multimodal audio-visual speech recognition (AVSR) In particular, we first train audio and visual encoders on a large-scale uni-modal dataset, then we integrate components of both encoders into a larger multimodal framework. Our model is experimentally validated on both word-level and sentence-level AVSR tasks.
  arXiv  Detail & Related papers  (2022-02-24T15:12:17Z)
• Jointly Fine-Tuning "BERT-like" Self Supervised Models to Improve Multimodal Speech Emotion Recognition [9.099532309489996]
  We show that jointly fine-tuning "BERT-like" SSL architectures achieve state-of-the-art (SOTA) results. We also evaluate two methods of fusing speech and text modalities and show that a simple fusion mechanism can outperform more complex ones.
  arXiv  Detail & Related papers  (2020-08-15T08:54:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.