Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts

• URL: http://arxiv.org/abs/2508.10009v1
• Date: Tue, 05 Aug 2025 23:56:11 GMT
• Title: Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts
• Authors: Hojun Jin, Eunsoo Hong, Ziwon Hyung, Sungjun Lim, Seungjin Lee, Keunseok Cho,
• Abstract summary: We propose a simple yet effective Supervised Mixture of Experts (S-MoE)<n>S-MoE eliminates the need for training gating functions by utilizing special guiding tokens to route each task to its designated expert.<n>We apply S-MoE to a speech-to-text model, enabling the model to process mixed-bandwidth input while jointly performing automatic speech recognition (ASR) and speech translation (ST)
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Hard-parameter sharing is a common strategy to train a single model jointly across diverse tasks. However, this often leads to task interference, impeding overall model performance. To address the issue, we propose a simple yet effective Supervised Mixture of Experts (S-MoE). Unlike traditional Mixture of Experts models, S-MoE eliminates the need for training gating functions by utilizing special guiding tokens to route each task to its designated expert. By assigning each task to a separate feedforward network, S-MoE overcomes the limitations of hard-parameter sharing. We further apply S-MoE to a speech-to-text model, enabling the model to process mixed-bandwidth input while jointly performing automatic speech recognition (ASR) and speech translation (ST). Experimental results demonstrate the effectiveness of the proposed S-MoE, achieving a 6.35% relative improvement in Word Error Rate (WER) when applied to both the encoder and decoder.

Related papers

• A Mixture-of-Experts Model for Multimodal Emotion Recognition in Conversations [24.302280709646563]
  We propose a modular Mixture-of-Experts for Recognition of Emotions (MiSTER-E) framework to decouple two core challenges in Emotion Recognition in Conversations (ERC)<n>MiSTER-E leverages large language models (LLMs) fine-tuned for both speech and text to provide rich utterance-level embeddings.<n>The system integrates predictions from three experts-speech-only, text-only, and cross-modal-using a learned gating mechanism.
  arXiv  Detail & Related papers  (2026-02-26T18:08:40Z)
• 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)
• Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts [22.936728143586443]
  Multi-task learning (MTL) for dense prediction has shown promising results but still faces challenges in balancing shared representations with task-specific specialization.<n>We introduce a novel Fine-Grained Mixture of Experts architecture that explores MoE-based MTL models through a combination of three key innovations and fine-tuning.
  arXiv  Detail & Related papers  (2025-07-25T08:59:30Z)
• SM3Det: A Unified Model for Multi-Modal Remote Sensing Object Detection [79.58755811919366]
  This paper introduces a new task called Multi-Modal datasets and Multi-Task Object Detection (M2Det) for remote sensing.<n>It is designed to accurately detect horizontal or oriented objects from any sensor modality.<n>This task poses challenges due to 1) the trade-offs involved in managing multi-modal modelling and 2) the complexities of multi-task optimization.
  arXiv  Detail & Related papers  (2024-12-30T02:47:51Z)
• Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging [111.8456671452411]
  Multi-task learning (MTL) leverages a shared model to accomplish multiple tasks and facilitate knowledge transfer. We propose a Weight-Ensembling Mixture of Experts (WEMoE) method for multi-task model merging. We show that WEMoE and E-WEMoE outperform state-of-the-art (SOTA) model merging methods in terms of MTL performance, generalization, and robustness.
  arXiv  Detail & Related papers  (2024-10-29T07:16:31Z)
• Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models [33.834215393960605]
  We introduce the Dynamic Mixture of Experts (DynMoE) technique.<n>DynMoE incorporates a novel gating method that enables each token to automatically determine the number of experts to activate.<n>We show the effectiveness of our approach to achieve competitive performance compared to GMoE for vision and language tasks, and MoE-LLaVA for vision-language tasks.
  arXiv  Detail & Related papers  (2024-05-23T08:18:30Z)
• Multi-Head Mixture-of-Experts [100.60556163597946]
  We propose Multi-Head Mixture-of-Experts (MH-MoE), which employs a multi-head mechanism to split each token into multiple sub-tokens. MH-MoE is straightforward to implement and decouples from other SMoE optimization methods, making it easy to integrate with other SMoE models for enhanced performance.
  arXiv  Detail & Related papers  (2024-04-23T13:47:09Z)
• Merging Multi-Task Models via Weight-Ensembling Mixture of Experts [64.94129594112557]
  Merging Transformer-based models trained on different tasks into a single unified model can execute all the tasks concurrently. Previous methods, exemplified by task arithmetic, have been proven to be both effective and scalable. We propose to merge most of the parameters while upscaling the Transformer layers to a weight-ensembling mixture of experts (MoE) module.
  arXiv  Detail & Related papers  (2024-02-01T08:58:57Z)
• Mod-Squad: Designing Mixture of Experts As Modular Multi-Task Learners [74.92558307689265]
  We propose Mod-Squad, a new model that is Modularized into groups of experts (a 'Squad') We optimize this matching process during the training of a single model. Experiments on the Taskonomy dataset with 13 vision tasks and the PASCAL-Context dataset with 5 vision tasks show the superiority of our approach.
  arXiv  Detail & Related papers  (2022-12-15T18:59:52Z)

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.