AuRA: Internalizing Audio Understanding into LLMs as LoRA

• URL: http://arxiv.org/abs/2606.11033v1
• Date: Tue, 09 Jun 2026 16:05:23 GMT
• Title: AuRA: Internalizing Audio Understanding into LLMs as LoRA
• Abstract summary: We present AuRA, a method that distills audio encoding capability into the large language models (LLMs)<n>Specifically, AuRA feeds the same speech input to an ASR encoder (as a teacher) and a LoRA-adapted LLM (as a student) through a lightweight audio embedding layer.<n>Compared with cascaded and serial bridge methods, AuRA enables tighter speech-language joint modeling and efficient parallel end-to-end inference.
• Score: 33.69997921138135
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent efforts to extend large language models (LLMs) to speech inputs typically rely on cascaded ASR-LLM pipelines, end-to-end speech-language models, or bridge/distillation-based adaptation. While these routes respectively reuse strong pretrained components, enable native speech-language interaction, or offer lightweight adaptation, they often suffer from transcript-interface latency, costly multimodal training, or sequential speech-language coupling. To address these limitations, we present AuRA, a method that distills audio encoding capability into the LLM. Specifically, AuRA feeds the same speech input to an ASR encoder (as a teacher) and a LoRA-adapted LLM (as a student) through a lightweight audio embedding layer, and uses layer-wise distillation to align the student's hidden states with corresponding teacher representations, thereby internalizing speech representations into lightweight LLM-side adaptations. Compared with cascaded and serial bridge methods, AuRA enables tighter speech-language joint modeling and efficient parallel end-to-end inference, while also reusing pretrained speech and language models rather than requiring large-scale multimodal training. On multiple speech-language benchmarks, AuRA consistently outperforms cascaded systems, speech-to-LLM adaptation baselines, and large-scale speech-language and multimodal models in both effectiveness and efficiency.

Related papers

• FastSLM: Hierarchical Frame Q-Former for Effective Speech Modality Adaptation [3.8125534288516683]
  FastSLM is a lightweight yet efficient speech-language model (SLM) designed for effective understanding and reasoning over long-form speech.<n>We present a novel three-stage training strategy that enhances generalization across a wide range of speech-related tasks.<n> Experimental results demonstrate that FastSLM achieves competitive performance compared to existing state-of-the-art models.
  arXiv  Detail & Related papers  (2026-01-08T07:46:03Z)
• Speech Recognition With LLMs Adapted to Disordered Speech Using Reinforcement Learning [13.113505050543298]
  We introduce a large language model capable of processing speech inputs.<n>We show that tuning it further with reinforcement learning on human preference enables it to adapt better to disordered speech than traditional fine-tuning.
  arXiv  Detail & Related papers  (2024-12-25T00:16:22Z)
• MSA-ASR: Efficient Multilingual Speaker Attribution with frozen ASR Models [59.80042864360884]
  Speaker-attributed automatic speech recognition (SA-ASR) aims to transcribe speech while assigning transcripts to the corresponding speakers accurately.<n>This paper introduces a novel approach, leveraging a frozen multilingual ASR model to incorporate speaker attribution into the transcriptions.
  arXiv  Detail & Related papers  (2024-11-27T09:01:08Z)
• DeSTA2: Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data [84.01401439030265]
  Recent end-to-end speech language models (SLMs) have expanded upon the capabilities of large language models (LLMs)<n>We present a simple yet effective automatic process for creating speech-text pair data.<n>Our model demonstrates general capabilities for speech-related tasks without the need for speech instruction-tuning data.
  arXiv  Detail & Related papers  (2024-09-30T07:01:21Z)
• Large Language Models are Strong Audio-Visual Speech Recognition Learners [53.142635674428874]
  Multimodal large language models (MLLMs) have recently become a focal point of research due to their formidable multimodal understanding capabilities.<n>We propose Llama-AVSR, a new MLLM with strong audio-visual speech recognition capabilities.<n>We evaluate our proposed approach on LRS3, the largest public AVSR benchmark, and we achieve new state-of-the-art results for the tasks of ASR and AVSR with a WER of 0.79% and 0.77%, respectively.
  arXiv  Detail & Related papers  (2024-09-18T21:17:27Z)
• Large Language Model Can Transcribe Speech in Multi-Talker Scenarios with Versatile Instructions [68.98811048970963]
  We present a pioneering effort to investigate the capability of large language models (LLMs) in transcribing speech in multi-talker environments.<n>We use WavLM and Whisper encoder to extract multi-faceted speech representations that are sensitive to speaker characteristics and semantic context.<n>Experiments reveal the promising performance of our proposed system, MT-LLM, in cocktail party scenarios.
  arXiv  Detail & Related papers  (2024-09-13T07:28:28Z)
• Boosting Large Language Model for Speech Synthesis: An Empirical Study [86.89548753080432]
  Large language models (LLMs) have made significant advancements in natural language processing and are concurrently extending the language ability to other modalities, such as speech and vision. We conduct a comprehensive empirical exploration of boosting LLMs with the ability to generate speech, by combining pre-trained LLM LLaMA/OPT and text-to-speech synthesis model VALL-E. We compare three integration methods between LLMs and speech models, including directly fine-tuned LLMs, superposed layers of LLMs and VALL-E, and coupled LLMs and VALL-E using LLMs as a powerful text encoder
  arXiv  Detail & Related papers  (2023-12-30T14:20:04Z)
• Prompting Large Language Models with Speech Recognition Abilities [31.77576008965215]
  We extend the capabilities of large language models by directly attaching a small audio encoder allowing it to perform speech recognition. Experiments on MultilingualSpeech show that incorporating a conformer encoder into the open sourced LLaMA-7B allows it to outperform monolingual baselines by 18%.
  arXiv  Detail & Related papers  (2023-07-21T08:39:15Z)
• On decoder-only architecture for speech-to-text and large language model integration [59.49886892602309]
  Speech-LLaMA is a novel approach that effectively incorporates acoustic information into text-based large language models. We conduct experiments on multilingual speech-to-text translation tasks and demonstrate a significant improvement over strong baselines.
  arXiv  Detail & Related papers  (2023-07-08T06:47:58Z)

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.