@inproceedings{ensan-etal-2026-intent,
title = "Intent Recognition in Speech-to-Text Processing in the Context of Natural Interaction with Cognitive Assistive Systems",
author = "Ensan, Behnam and
Jung, Magnus and
Busch, Matthias and
Wendemuth, Adreas",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.793/",
doi = "10.63317/2ekx6bohnzso",
pages = "10102--10113",
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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ensan-etal-2026-intent">
<titleInfo>
<title>Intent Recognition in Speech-to-Text Processing in the Context of Natural Interaction with Cognitive Assistive Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Behnam</namePart>
<namePart type="family">Ensan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Magnus</namePart>
<namePart type="family">Jung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Busch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adreas</namePart>
<namePart type="family">Wendemuth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">ensan-etal-2026-intent</identifier>
<identifier type="doi">10.63317/2ekx6bohnzso</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.793/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>10102</start>
<end>10113</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Intent Recognition in Speech-to-Text Processing in the Context of Natural Interaction with Cognitive Assistive Systems
%A Ensan, Behnam
%A Jung, Magnus
%A Busch, Matthias
%A Wendemuth, Adreas
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F ensan-etal-2026-intent
%X 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.
%R 10.63317/2ekx6bohnzso
%U https://aclanthology.org/2026.lrec-1.793/
%U https://doi.org/10.63317/2ekx6bohnzso
%P 10102-10113
Markdown (Informal)
[Intent Recognition in Speech-to-Text Processing in the Context of Natural Interaction with Cognitive Assistive Systems](https://aclanthology.org/2026.lrec-1.793/) (Ensan et al., LREC 2026)
ACL