Optimal Transport Regularization for Speech Text Alignment in Spoken Language Models

TL;DR

This paper introduces Optimal Transport Regularization (OTReg), a novel method that aligns speech and text representations in spoken language models to improve their generalization across datasets.

Contribution

The paper proposes OTReg, a lightweight, label-free regularization technique that formulates speech-text alignment as an optimal transport problem within SLM training.

Findings

OTReg improves speech-text alignment in multilingual ASR tasks.

OTReg enhances SLM generalization across diverse datasets.

OTReg reduces the modality gap between speech and text representations.

Abstract

Spoken Language Models (SLMs), which extend Large Language Models (LLMs) to perceive speech inputs, have gained increasing attention for their potential to advance speech understanding tasks. However, despite recent progress, studies show that SLMs often struggle to generalize across datasets, even for trained languages and tasks, raising concerns about whether they process speech in a text-like manner as intended. A key challenge underlying this limitation is the modality gap between speech and text representations. The high variability in speech embeddings may allow SLMs to achieve strong in-domain performance by exploiting unintended speech variations, ultimately hindering generalization. To mitigate this modality gap, we introduce Optimal Transport Regularization (OTReg), a method that formulates speech-text alignment as an optimal transport problem and derives a regularization loss to improve SLM training. In each training iteration, OTReg first establishes a structured correspondence between speech and transcript embeddings by determining the optimal transport plan, then incorporates the regularization loss based on this transport plan to optimize SLMs in generating speech embeddings that align more effectively with transcript embeddings. OTReg is lightweight, requiring no additional labels or learnable parameters, and integrates seamlessly into existing SLM training procedures. Extensive multilingual ASR experiments demonstrate that OTReg enhances speech-text alignment, mitigates the modality gap, and consequently improves SLM generalization across diverse datasets.