# Distilling an End-to-End Voice Assistant Without Instruction Training Data

arXiv: https://arxiv.org/abs/2410.02678 · HTML: https://mlsanity.com/paper/2410.02678/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 60 references that are in the map.
- First posted on arXiv 3 Oct 2024.

## Builds on (most cited first, 30 of 47)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Bag of Tricks for Efficient Text Classification](https://mlsanity.com/paper/1607.01759/) (2016)
- [MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations](https://mlsanity.com/paper/1810.02508/) (2018)
- [AST: Audio Spectrogram Transformer](https://mlsanity.com/paper/2104.01778/) (2021)
- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [SALMONN: Towards Generic Hearing Abilities for Large Language Models](https://mlsanity.com/paper/2310.13289/) (2023)
- [TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages](https://mlsanity.com/paper/2003.05002/) (2020)
- [MLS: A Large-Scale Multilingual Dataset for Speech Research](https://mlsanity.com/paper/2012.03411/) (2020)
- [GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio](https://mlsanity.com/paper/2106.06909/) (2021)
- [Learning to Compress Prompts with Gist Tokens](https://mlsanity.com/paper/2304.08467/) (2023)
- [Pengi: An Audio Language Model for Audio Tasks](https://mlsanity.com/paper/2305.11834/) (2023)
- [Listen, Think, and Understand](https://mlsanity.com/paper/2305.10790/) (2023)
- [SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing](https://mlsanity.com/paper/2110.07205/) (2021)
- [Towards Multimodal Sarcasm Detection (An _Obviously_ Perfect Paper)](https://mlsanity.com/paper/1906.01815/) (2019)
- [On decoder-only architecture for speech-to-text and large language model integration](https://mlsanity.com/paper/2307.03917/) (2023)
- [Prompting Large Language Models with Speech Recognition Abilities](https://mlsanity.com/paper/2307.11795/) (2023)
- [UR-FUNNY: A Multimodal Language Dataset for Understanding Humor](https://mlsanity.com/paper/1904.06618/) (2019)
- [The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage](https://mlsanity.com/paper/2111.09344/) (2021)
- [EmotionLines: An Emotion Corpus of Multi-Party Conversations](https://mlsanity.com/paper/1802.08379/) (2018)

## Built on by (most cited first, 30 of 39)

- [VoiceBench: Benchmarking LLM-Based Voice Assistants](https://mlsanity.com/paper/2410.17196/) (2024)
- [On The Landscape of Spoken Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2504.08528/) (2025)
- [DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment](https://mlsanity.com/paper/2507.02768/) (2025)
- [Multilingual and Multi-Accent Jailbreaking of Audio LLMs](https://mlsanity.com/paper/2504.01094/) (2025)
- [Speech-IFEval: Evaluating Instruction-Following and Quantifying Catastrophic Forgetting in Speech-Aware Language Models](https://mlsanity.com/paper/2505.19037/) (2025)
- [Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models](https://mlsanity.com/paper/2505.15406/) (2025)
- [AudioJudge: Understanding What Works in Large Audio Model Based Speech Evaluation](https://mlsanity.com/paper/2507.12705/) (2025)
- [Closing the Gap Between Text and Speech Understanding in LLMs](https://mlsanity.com/paper/2510.13632/) (2025)
- [Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models](https://mlsanity.com/paper/2412.13702/) (2024)
- [MERaLiON-AudioLLM: Bridging Audio and Language with Large Language Models](https://mlsanity.com/paper/2412.09818/) (2024)
- [Contrastive Learning for Task-Independent SpeechLLM-Pretraining](https://mlsanity.com/paper/2412.15712/) (2024)
- [Mind the Gap! Static and Interactive Evaluations of Large Audio Models](https://mlsanity.com/paper/2502.15919/) (2025)
- [DIFFA: Large Language Diffusion Models Can Listen and Understand](https://mlsanity.com/paper/2507.18452/) (2025)
- [SARSteer: Safeguarding Large Audio-Language Models via Safe-Ablated Refusal Steering](https://mlsanity.com/paper/2510.17633/) (2025)
- [SeaLLMs-Audio: Large Audio-Language Models for Southeast Asia](https://mlsanity.com/paper/2511.01670/) (2025)
- [SpidR: Learning Fast and Stable Linguistic Units for Spoken Language Models Without Supervision](https://mlsanity.com/paper/2512.20308/) (2025)
- [ESPnet-SDS: Unified Toolkit and Demo for Spoken Dialogue Systems](https://mlsanity.com/paper/2503.08533/) (2025)
- [From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Data](https://mlsanity.com/paper/2505.20166/) (2025)
- [How Contrastive Decoding Enhances Large Audio Language Models](https://mlsanity.com/paper/2603.09232/) (2026)
- [DuplexMamba: Enhancing Real-time Speech Conversations with Duplex and Streaming Capabilities](https://mlsanity.com/paper/2502.11123/) (2025)
- [Chain-of-Thought Training for Open E2E Spoken Dialogue Systems](https://mlsanity.com/paper/2506.00722/) (2025)
- [Speechless: Speech Instruction Training Without Speech for Low Resource Languages](https://mlsanity.com/paper/2505.17417/) (2025)
- [DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding](https://mlsanity.com/paper/2601.23161/) (2026)
- [ERIS: Evolutionary Real-world Interference Scheme for Jailbreaking Audio Large Models](https://mlsanity.com/paper/2509.11128/) (2025)
- [GRM: Utility-Aware Jailbreak Attacks on Audio LLMs via Gradient-Ratio Masking](https://mlsanity.com/paper/2604.09222/) (2026)
- [Minimizing Modality Gap from the Input Side: Your Speech LLM Can Be a Prosody-Aware Text LLM](https://mlsanity.com/paper/2605.05927/) (2026)
- [TESU-LLM: Training Speech-LLMs Without Speech via Unified Encoder Alignment](https://mlsanity.com/paper/2506.06343/) (2025)
- [The Alignment Curse: Modality Alignment Supercharges Audio Attacks via Text Transfer](https://mlsanity.com/paper/2602.02557/) (2026)
- [Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision](https://mlsanity.com/paper/2603.07025/) (2026)
- [AuRA: Internalizing Audio Understanding into LLMs as LoRA](https://mlsanity.com/paper/2606.11033/) (2026)

## Abstract (arXiv)

Voice assistants, such as Siri and Google Assistant, typically model audio and text separately, resulting in lost speech information and increased complexity. Recent efforts to address this with end-to-end Speech Large Language Models (LLMs) trained with supervised finetuning (SFT) have led to models ``forgetting" capabilities from text-only LLMs. Our work proposes an alternative paradigm for training Speech LLMs without instruction data, using the response of a text-only LLM to transcripts as self-supervision. Importantly, this process can be performed without annotated responses. We show that our Distilled Voice Assistant (DiVA) generalizes to Spoken Question Answering, Classification, and Translation. Furthermore, we show that DiVA better meets user preferences, achieving a 72% win rate compared with state-of-the-art models like Qwen 2 Audio, despite using >100x less training compute.