# HarmoniFuse: A Component-Selective and Prompt-Adaptive Framework for Multi-Task Speech Language Modeling

arXiv: https://arxiv.org/abs/2509.18570 · HTML: https://mlsanity.com/paper/2509.18570/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 24 references that are in the map.
- First posted on arXiv 23 Sep 2025.

## Builds on (most cited first, 17 of 17)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [Qwen2-Audio Technical Report](https://mlsanity.com/paper/2407.10759/) (2024)
- [SALMONN: Towards Generic Hearing Abilities for Large Language Models](https://mlsanity.com/paper/2310.13289/) (2023)
- [Pengi: An Audio Language Model for Audio Tasks](https://mlsanity.com/paper/2305.11834/) (2023)
- [emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation](https://mlsanity.com/paper/2312.15185/) (2023)
- [Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation](https://mlsanity.com/paper/2407.05361/) (2024)
- [SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing](https://mlsanity.com/paper/2110.07205/) (2021)
- [Emotion Recognition from Speech Using Wav2vec 2.0 Embeddings](https://mlsanity.com/paper/2104.03502/) (2021)
- [FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs](https://mlsanity.com/paper/2407.04051/) (2024)
- [Exploring Wav2vec 2.0 fine-tuning for improved speech emotion recognition](https://mlsanity.com/paper/2110.06309/) (2021)
- [Speech Emotion Recognition with Co-Attention based Multi-level Acoustic Information](https://mlsanity.com/paper/2203.15326/) (2022)
- [Fusing ASR Outputs in Joint Training for Speech Emotion Recognition](https://mlsanity.com/paper/2110.15684/) (2021)
- [A layer-wise analysis of Mandarin and English suprasegmentals in SSL speech models](https://mlsanity.com/paper/2408.13678/) (2024)
- [Speech Emotion Recognition with ASR Transcripts: A Comprehensive Study on Word Error Rate and Fusion Techniques](https://mlsanity.com/paper/2406.08353/) (2024)
- [PolySpeech: Exploring Unified Multitask Speech Models for Competitiveness with Single-task Models](https://mlsanity.com/paper/2406.07801/) (2024)

## Abstract (arXiv)

Recent advances in large language models have facilitated the development of unified speech language models (SLMs) capable of supporting multiple speech tasks within a shared architecture. However, tasks such as automatic speech recognition (ASR) and speech emotion recognition (SER) rely on distinct types of information: ASR primarily depends on linguistic content, whereas SER requires the integration of both linguistic and paralinguistic cues. Existing multitask SLMs typically adopt naive parameter sharing or prompt-based conditioning without explicitly modeling the differences in information composition required by each task. Such designs risk task interference and performance degradation, especially under limited data conditions. To address these limitations, we propose HarmoniFuse, a component-selective and prompt-adaptive framework for multi-task speech language modeling. HarmoniFuse is designed to harmonize heterogeneous task demands by selecting and fusing task-relevant components of speech representations. Specifically, it integrates a gated speech encoder to extract task-specific acoustic features and a prompt-adaptive dynamic fusion module to aggregate transformer layers based on task characteristics. In addition, a batch-interleaved training strategy enables leveraging separate ASR and SER datasets without requiring joint annotation. Experimental results demonstrate that HarmoniFuse improves both ASR and SER performance, offering a scalable and robust solution for multitask speech understanding under realistic data constraints.