Performance Evaluation of SLAM-ASR: The Good, the Bad, the Ugly, and the Way Forward

Performance Evaluation of SLAM-ASR: The Good, the Bad, the Ugly, and the Way Forward

Stať ve sborníku v databázi WoS či Scopus

Recent research has demonstrated that training a linear connector between speech foundation encoders and large language models (LLMs) enables this architecture to achieve strong ASR capabilities. Despite the impressive results, it remains unclear whether these simple approaches are robust enough across different scenarios and speech conditions, such as domain shifts and speech perturbations. In this paper, we address these questions by conducting various ablation experiments using a recent and widely adopted approach called SLAM-ASR. We present novel empirical findings that offer insights on how to effectively utilize the SLAM-ASR architecture across a wide range of settings. Our main findings indicate that SLAM-ASR exhibits poor performance in cross-domain evaluation settings. Additionally, speech perturbations on in-domain data, such as changes in speech rate or additive noise, can significantly degrade performance. Our findings offer critical insights for fine-tuning and configuring robust LLM-based ASR models, tailored to different data characteristics and computational resources.

Recent research has demonstrated that training a linear connector between speech foundation encoders and large language models (LLMs) enables this architecture to achieve strong ASR capabilities. Despite the impressive results, it remains unclear whether these simple approaches are robust enough across different scenarios and speech conditions, such as domain shifts and speech perturbations. In this paper, we address these questions by conducting various ablation experiments using a recent and widely adopted approach called SLAM-ASR. We present novel empirical findings that offer insights on how to effectively utilize the SLAM-ASR architecture across a wide range of settings. Our main findings indicate that SLAM-ASR exhibits poor performance in cross-domain evaluation settings. Additionally, speech perturbations on in-domain data, such as changes in speech rate or additive noise, can significantly degrade performance. Our findings offer critical insights for fine-tuning and configuring robust LLM-based ASR models, tailored to different data characteristics and computational resources.

ASR, LLMs, embeddings, speech-to-text alignment, foundation models

ASR, LLMs, embeddings, speech-to-text alignment, foundation models

KUMAR, S.; THORBECKE, I.; BURDISSO, S.; VILLATORO-TELLO, E.; MANJUNATH, K.; HACIOGLU, K.; RANGAPPA, P.; MOTLÍČEK, P.; GANAPATHIRAJU, A.; STOLCKE, A.

2026

06.04.2025

IEEE

Hyderabad, Indická republika

979-8-3315-1932-2

2025 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING WORKSHOPS, ICASSPW

1

5

5

https://www.fit.vut.cz/research/group/speech/public/publi/2025/kumar_interspeech2025_co-author_Motlicek.pdf

kumar_interspeech2025_co-author_Motlicek