Talking to Robots: A Practical Examination of Speech Foundation Models for HRI Applications
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908500946321408 |
|---|---|
| author | Rosin, Theresa Pekarek Gachot, Julia Kordt, Henri-Leon Kerzel, Matthias Wermter, Stefan |
| author_facet | Rosin, Theresa Pekarek Gachot, Julia Kordt, Henri-Leon Kerzel, Matthias Wermter, Stefan |
| contents | Automatic Speech Recognition (ASR) systems in real-world settings need to handle imperfect audio, often degraded by hardware limitations or environmental noise, while accommodating diverse user groups. In human-robot interaction (HRI), these challenges intersect to create a uniquely challenging recognition environment. We evaluate four state-of-the-art ASR systems on eight publicly available datasets that capture six dimensions of difficulty: domain-specific, accented, noisy, age-variant, impaired, and spontaneous speech. Our analysis demonstrates significant variations in performance, hallucination tendencies, and inherent biases, despite similar scores on standard benchmarks. These limitations have serious implications for HRI, where recognition errors can interfere with task performance, user trust, and safety. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_17753 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Talking to Robots: A Practical Examination of Speech Foundation Models for HRI Applications Rosin, Theresa Pekarek Gachot, Julia Kordt, Henri-Leon Kerzel, Matthias Wermter, Stefan Robotics Artificial Intelligence Computation and Language Human-Computer Interaction Automatic Speech Recognition (ASR) systems in real-world settings need to handle imperfect audio, often degraded by hardware limitations or environmental noise, while accommodating diverse user groups. In human-robot interaction (HRI), these challenges intersect to create a uniquely challenging recognition environment. We evaluate four state-of-the-art ASR systems on eight publicly available datasets that capture six dimensions of difficulty: domain-specific, accented, noisy, age-variant, impaired, and spontaneous speech. Our analysis demonstrates significant variations in performance, hallucination tendencies, and inherent biases, despite similar scores on standard benchmarks. These limitations have serious implications for HRI, where recognition errors can interfere with task performance, user trust, and safety. |
| title | Talking to Robots: A Practical Examination of Speech Foundation Models for HRI Applications |
| topic | Robotics Artificial Intelligence Computation and Language Human-Computer Interaction |
| url | https://arxiv.org/abs/2508.17753 |