# How to Leverage Synthetic Speech for LLM-Based ASR Systems?

arXiv: https://arxiv.org/abs/2606.29031 · HTML: https://mlsanity.com/paper/2606.29031/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 43 references that are in the map.
- First posted on arXiv 27 Jun 2026.

## Builds on (most cited first, 30 of 35)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [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)
- [SUPERB: Speech processing Universal PERformance Benchmark](https://mlsanity.com/paper/2105.01051/) (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)
- [UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022](https://mlsanity.com/paper/2204.02152/) (2022)
- [AudioPaLM: A Large Language Model That Can Speak and Listen](https://mlsanity.com/paper/2306.12925/) (2023)
- [CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens](https://mlsanity.com/paper/2407.05407/) (2024)
- [Layer-wise Analysis of a Self-supervised Speech Representation Model](https://mlsanity.com/paper/2107.04734/) (2021)
- [XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model](https://mlsanity.com/paper/2406.04904/) (2024)
- [NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality](https://mlsanity.com/paper/2205.04421/) (2022)
- [Qwen3-TTS Technical Report](https://mlsanity.com/paper/2601.15621/) (2026)
- [IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech](https://mlsanity.com/paper/2506.21619/) (2025)
- [Speech Recognition with Augmented Synthesized Speech](https://mlsanity.com/paper/1909.11699/) (2019)
- [Generating Synthetic Audio Data for Attention-Based Speech Recognition Systems](https://mlsanity.com/paper/1912.09257/) (2019)
- [Building and Evaluation of a Real Room Impulse Response Dataset](https://mlsanity.com/paper/1811.06795/) (2018)
- [Large-Scale Self- and Semi-Supervised Learning for Speech Translation](https://mlsanity.com/paper/2104.06678/) (2021)
- [Speech Self-Supervised Representation Benchmarking: Are We Doing it Right?](https://mlsanity.com/paper/2306.00452/) (2023)
- [OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models](https://mlsanity.com/paper/2604.00688/) (2026)
- [Task Arithmetic can Mitigate Synthetic-to-Real Gap in Automatic Speech Recognition](https://mlsanity.com/paper/2406.02925/) (2024)
- [Enhancing Low-Resource ASR through Versatile TTS: Bridging the Data Gap](https://mlsanity.com/paper/2410.16726/) (2024)
- [Text-only adaptation in LLM-based ASR through text denoising](https://mlsanity.com/paper/2601.20900/) (2026)
- [A Self-Refining Framework for Enhancing ASR Using TTS-Synthesized Data](https://mlsanity.com/paper/2506.11130/) (2025)
- [Geometric Alignment without Functional Equivalence: A Layer-wise Analysis of the Speech-Text Modality Gap](https://mlsanity.com/paper/2603.01502/) (2026)
- [Towards Explicit Acoustic Evidence Perception in Audio LLMs for Speech Deepfake Detection](https://mlsanity.com/paper/2601.23066/) (2026)
- [Towards Explainable Spoofed Speech Attribution and Detection:a Probabilistic Approach for Characterizing Speech Synthesizer Components](https://mlsanity.com/paper/2502.04049/) (2025)
- [The State Of TTS: A Case Study with Human Fooling Rates](https://mlsanity.com/paper/2508.04179/) (2025)

## Built on by (most cited first, 1 of 1)

- [When Synthetic Speech Is All You Have: Better Call GRPO](https://mlsanity.com/paper/2607.08409/) (2026)

## Abstract (arXiv)

In regulated domains such as banking and healthcare, where privacy constraints make real speech costly to collect and retain, synthetic speech from modern text-to-speech (TTS) is an appealing alternative for training automatic speech recognition (ASR) without exposing sensitive customer recordings. Yet a persistent distributional gap between synthetic and real data limits how far it can replace genuine recordings. Prior work largely treats this gap as a black box to be engineered around, but in our work, we instead examine its origin directly by probing a SLAM-ASR architecture. Then, we localise where its LLM backbone separates real from synthetic speech and find the discriminative signal concentrated in the early-to-middle layers, where temporal and prosodic perturbations disrupt it most. We further show that representation-level separability, help, but does not directly predict downstream ASR gains. On the other hand, convolving synthetic audio with room impulse responses (RIRs) narrows the gap not by making synthetic speech sound cleaner or more natural, but by reproducing the acoustic irregularities of real recordings. Translating these findings into the training procedure, by adding a layer-selection module combined with RIR augmentation matches a fully real-data baseline using only 25% of the real speech (13.6h) and surpasses it at all higher proportions.