Abstract
While Automatic Speech Recognition (ASR) systems excel in controlled environments, challenges arise in robot-specific setups due to unique microphone requirements and added noise sources. In this paper, we create a dataset of initiating conversations with brief exchanges in 5 European languages, and we systematically evaluate current state-of-art ASR systems (Vosk, OpenWhisper, Google Speech and NVidia Riva). Besides standard metrics, we also look at two critical downstream tasks for human-robot verbal interaction: intent recognition rate and entity extraction, using the open-source Rasa chatbot. Overall, we found that open-source solutions as Vosk performs competitively with closed-source solutions while running on the edge, on a low compute budget (CPU only).
Original language | English |
---|---|
Title of host publication | HRI 2024 - Proceedings of the 2024 ACM/IEEE International Conference on Human-Robot Interaction |
Publisher | IEEE Computer Society |
Pages | 865-869 |
Number of pages | 5 |
ISBN (Electronic) | 9798400703225 |
DOIs | |
State | Published - 11 Mar 2024 |
Event | 19th Annual ACM/IEEE International Conference on Human-Robot Interaction, HRI 2024 - Boulder, United States Duration: 11 Mar 2024 → 15 Mar 2024 |
Publication series
Name | ACM/IEEE International Conference on Human-Robot Interaction |
---|---|
ISSN (Electronic) | 2167-2148 |
Conference
Conference | 19th Annual ACM/IEEE International Conference on Human-Robot Interaction, HRI 2024 |
---|---|
Country/Territory | United States |
City | Boulder |
Period | 11/03/24 → 15/03/24 |
Bibliographical note
Publisher Copyright:© 2024 IEEE Computer Society. All rights reserved.
Keywords
- Assistive Robotics
- Audio Dataset
- Automatic Speech Recognition
- Human-Robot Interaction
Fingerprint
Dive into the research topics of 'Dataset and Evaluation of Automatic Speech Recognition for Multi-lingual Intent Recognition on Social Robots'. Together they form a unique fingerprint.Datasets
-
ARImulti-mic: real-world speech recordings on a humanoid robot (ARI)
אופוצ'ינסקי, ר. (Creator), Moradi, M. (Creator) & Gannot, S. (Creator), IEEE DataPort, 1 Jan 2023
DOI: 10.21227/kyt6-zp69, https://ieee-dataport.org/documents/arimulti-mic-real-world-speech-recordings-humanoid-robot-ari
Dataset