arXiv Machine Learning

Text-only adaptation in LLM-based ASR through text denoising

arXiv Computation and Language
Sep 22

Closing the Speech-Text Gap with Limited Audio for Effective Domain Adaptation in LLM-Based ASR

arXiv:2604.06487v2 Announce Type: replace Abstract: Conventional end-to-end automatic speech recognition (ASR) systems rely on paired speech-text data for domain adaptation. Recent LLM-based ASR arch...

By Thibault Ba\~neras-Roux, Sergio Burdisso, Esa\'u Villatoro-Tello, Dairazalia S\'anchez-Cort\'es, Shiran Liu, Severin Baroudi, Shashi Kumar, Hasindri Watawana, Manjunath K E, Kadri Hacioglu, Petr Motlicek, Andreas Stolcke
arXiv AI
Sep 4

Listen to the Latents: Self-Correcting Speech Recognition in Large Audio Language Models Through Hidden-State Interactions

The paper introduces Hybrid Search, a method that refines warm-initialized large language model (LLM) based automatic speech recognition (ASR) systems by exploiting interactions between ASR hidden states and the base LLM’s hidden states. By identifying tokens with high semantic dependence and selectively correcting them, the approach surpasses traditional global LLM‑correction techniques such as rescoring and late fusion. The study demonstrates that even after warm initialization, LLM‑based ASR models can further benefit from their base LLM during inference.

By Chan-Jan Hsu, Jaeyeon Kim, Chao-Han Huck Yang, Shinji Watanabe, Hung-yi Lee, Carlos Busso
arXiv AI
Aug 25

Do Spoken Language Models Hear Speech as They Read Text? Bridging Structural Gaps Between Speech and Text

The paper investigates how Spoken Language Models (SLMs) process speech compared to text, noting that current SLMs show weak alignment between speech and text representations despite strong downstream performance. The authors propose a framework that separates length mismatch from semantic alignment to better match speech and text representations. Experiments on multiple benchmarks demonstrate that this approach yields competitive results against strong baselines, highlighting the need to explicitly address structural differences between speech and text in SLM training.

By Hyeonyu Kim, Hwayeon Kim, Youngwon Choi, Myeongkyun Cho, Huu-Kim Nguyen
arXiv Computation and Language
Nov 2

Minimizing Modality Gap from the Input Side: Your Speech LLM Can Be a Prosody-Aware Text LLM

The paper introduces TextPro‑SLM, a speech large language model that reduces the modality gap by making spoken input resemble a prosody‑aware text LLM. It combines WhisperPro, a unified speech encoder that outputs synchronized text tokens and prosody embeddings, with an LLM backbone that retains the semantic power of the original text LLM while learning paralinguistic cues. Experiments demonstrate that TextPro‑SLM achieves the lowest modality gap among leading SLMs at both 3B and 7B scales, and performs strongly on paralinguistic understanding tasks using only about 1,000 hours of audio for training.

By Wenqian Cui, Xiao-Hui Li, Daxin Tan, Qiyong Zheng, Irwin King
arXiv Machine Learning
Jul 20

RobustSpeechFlow: Learning Robust Text-to-Speech Trajectories via Augmentation-based Contrastive Flow Matching

arXiv:2605. 22083v2 Announce Type: replace-cross Abstract: While flow-matching text-to-speech (TTS) achieves strong zero-shot speaker similarity and naturalness, it remains susceptible to content fidelity issues, particularly skip and repeat errors from imperfect alignment.

By Jinhyeok Yang, Hyeongju Kim, Yechan Yu, Joon Byun, Frederik Bous, Juheon Lee