Reliability of Speech Recognition for Conversational Human–Robot Interaction: A Multi-Corpus Analysis of Denoising, Voice Activity Detection, and Transcription
Applied Sciences · 13.11.2026 · 16 (22) · 11262
DOI: 10.3390/app162211262 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 13.11.2026. Verfasst von Subashkumar Rajanayagam und 2 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Research, Transfer, and Start-Up Center, Anhalt University of Applied Sciences, state of Saxony-Anhalt.
Abstract (Originalsprache)
Rising numbers of isolated nursing home residents and nursing staff shortages motivate voice-based conversational assistants for monitoring and companionship; both require reliable transcription without an enrolled speaker profile to reduce staff burden and serve as a baseline for speaker-based methods. We benchmarked a cascaded denoising, voice activity detection (VAD) and speech-to-text pipeline (DeepFilterNet3, Silero VAD, faster-whisper large-v3) at library defaults on five English corpora: utterance-based files (LibriSpeech, AMI clips on digital silence, LibriMix mixtures) and real recordings (CHiME-6). We report the pooled-count word error rate (WER) with cluster-bootstrap intervals, offline VAD F1 and embedding-based semantic error rate (SER). The best WER ranged from 4% on clean read speech to 68% on the CHiME-6 close-talk channel, whose reference omits other participants’ speech. External=VAD routing lowered WER in all 10 matched utterance-based comparisons (0.1 to 5.3 points); on CHiME-6 the effect depended on channel and reference (without denoising: close talk −65.3 points against the wearer’s reference, +12.4 against the all-participants reference; distant array +10.4). Denoising helped substantially only on the CHiME-6 close-talk channel. VAD F1 showed no consistent association with WER on utterance-based files (r = +0.11). The SER misses fluent fabrication. The findings suggest a provisional, in-sample rule needing held-out validation, including older-adult speech.
Förderung
- Research, Transfer, and Start-Up Center
- Anhalt University of Applied Sciences
- state of Saxony-Anhalt
- Bundesministerium Forschung, Technologie und Raumfahrt
- Open Access Publishing Fund of Anhalt University of Applied Sciences
Zitieren
APA
Rajanayagam, S., Tümler, J., & Twieg, S. (2026). Reliability of Speech Recognition for Conversational Human–Robot Interaction: A Multi-Corpus Analysis of Denoising, Voice Activity Detection, and Transcription. Applied Sciences, 16(22), 11262. https://doi.org/10.3390/app162211262
Vancouver
Rajanayagam S, Tümler J, Twieg S. Reliability of Speech Recognition for Conversational Human–Robot Interaction: A Multi-Corpus Analysis of Denoising, Voice Activity Detection, and Transcription. Applied Sciences. 2026;16(22):11262. doi:10.3390/app162211262
BibTeX
@article{Rajanayagam2026,
author = {Rajanayagam, Subashkumar and Tümler, Johannes and Twieg, Stefan},
title = {Reliability of Speech Recognition for Conversational Human–Robot Interaction: A Multi-Corpus Analysis of Denoising, Voice Activity Detection, and Transcription},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {22},
pages = {11262},
doi = {10.3390/app162211262}
}
EUVIMED