This method integrates the LMs directly into the parameters of an LLM-based ASR model, requiring no additional computational cost at inference, and consistently improved the ASR performance in the target domains, without degrading inference speed or memory footprint.
Abstract
Automatic speech recognition (ASR) systems, trained on paired speech-text data, have been improved by leveraging language models (LMs) trained on text-only data. LM fusion methods such as shallow fusion and density ratio are well-established methods that incorporate external LMs during ASR decoding. However, they incur additional computational costs due to LM inference, which is particularly problematic for recent larger LMs. In this study, we propose incorporating external LMs via model merging. This method integrates the LMs directly into the parameters of an LLM-based ASR model, requiring no additional computational cost at inference. We formulate domain extension and transfer via arithmetic operations on LoRA parameters. Experimental evaluations were conducted for the domain adaptation of LLM-based ASR trained on CSJ and LibriSpeech. We show that our LM merging consistently improved the ASR performance in the target domains, without degrading inference speed or memory footprint.
Large language models (LLMs) enhance automatic speech recognition (ASR) by providing linguistic priors; however, their direct rescoring is costly because it requires evaluating every N-best hypothesis. This paper introduces"cached LLM probability retrieval,"which involves querying a local teacher LLM offline to obtain...
This paper introduces a syllable-level UASR framework based on masked language modeling, which avoids the need for G2P and the instability of GAN-based methods and generalizes effectively to low-resource languages that have remained particularly difficult for prior methods.
Liming Wang, Kai-Wei Chang, K. Kashino et al.· 0 citations
Recent automatic speech recognition (ASR) systems increasingly integrate large language models (LLMs) to leverage their semantic knowledge, either externally through logit fusion or internally through warm initialization. However, how to effectively combine these two strategies remains underexplored. In this work, we r...
Chan-Jan Hsu, Jaeyeon Kim, Chao-Han Huck Yang et al.· 0 citations
This work studies two forms of demonstration, collated and interleaved demonstration, across six encoder-decoder models, spanning conventional cross-attention-based and LLM-based architectures and suggests that in-context adaptation for ASR is not unique to specific architectures, training, or demonstration approaches.
In recent years, the combination of large language model (LLM) and pre-trained voice encoder has shown great potential in the field of automatic speech recognition (ASR). However, bridging the modal communication between acoustic characterization and language embedding often requires a large number of training paramete...
Yuxi Li, Yan Wang· Applied and Computational En...· 0 citations
In recent years, automatic speech recognition (ASR) has witnessed transformative advancements driven by three complementary paradigms: data scaling, model scaling, and deep integration with large language models (LLMs). However, bridging the gap between academic benchmark performance and real-world production utility r...
Chuan-Meng Bian, Da-Ren Chen, Pei-Xin Chen et al.· 2 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduSep 24, 2026
A new method, called CW-Net, translates the reasoning process of an autonomous vehicle’s AI system into understandable concepts that explain its behavior.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
