Intent Recognition in Speech-to-Text Processing in the Context of Natural Interaction with Cognitive Assistive Systems

Behnam Ensan, Magnus Jung, Matthias Busch, Adreas Wendemuth


Abstract
This study investigates efficient speech-to-intent recognition for human–robot interaction in elderly-care environments in German, targeting deployment on resource-constrained platforms such as the Jetson AGX Orin. To benchmark performance, we created a domain-specific German dataset with two sub-datasets (PaSID and PaSynTex) that simulate specific nursing home communication scenarios. Two alternative speech-to-intent pipelines were developed and evaluated: a two-stage system combining automatic speech recognition (ASR) with a large language model (LLM), and an end-to-end large audio–language model (LALM) architecture. The performance of Whisper-based ASR systems was evaluated across a wide variety of LLMs and several LALMs, comparing intent-classification accuracy, latency, and resource efficiency. The results indicate that optimized ASR + LLM configurations, particularly Whisper Turbo coupled with Phi-3.5-mini or Qwen 2.5-7B, outperform unified LALM approaches while maintaining substantially lower memory and inference costs. Also, the analysis shows that, the unified LALM models outperform the two-step integration of ASR + LLM in the same configuration, but at the cost of higher resource utilization, likely due to limited optimization for edge deployment. Overall, the findings provide initial evidence that modular ASR + LLM pipelines provide a more practical solution for real-time, on-device intent recognition in assistive robotics in German, offering an effective trade-off between performance and deployability on resource-constrained platforms.
Anthology ID:
2026.lrec-1.793
Volume:
Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:
LREC
SIG:
Publisher:
ELRA Language Resource Association
Note:
Pages:
10102–10113
Language:
External URL:
https://lrec.elra.info/lrec2026-main-793
DOI:
10.63317/2ekx6bohnzso
Bibkey:
Cite (ACL):
Behnam Ensan, Magnus Jung, Matthias Busch, and Adreas Wendemuth. 2026. Intent Recognition in Speech-to-Text Processing in the Context of Natural Interaction with Cognitive Assistive Systems. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 10102–10113, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):
Intent Recognition in Speech-to-Text Processing in the Context of Natural Interaction with Cognitive Assistive Systems (Ensan et al., LREC 2026)
Copy Citation: