Borghi, Pedro HenriqueTeixeira, João PauloFreitas, Diamantino Rui2024-10-072024-10-072024Borghi, Pedro Henrique; Teixeira, João Paulo; Freitas, Diamantino Rui (2024). Automatic Speech Recognition for Portuguese: A Comparative Study. In 3rd International Conference on Optimization, Learning Algorithms and Applications (OL2A 2023). Cham: Springer Nature, Vol. 1, p. 217–232. ISBN 978-3-031-53024-1.978-3-031-53024-1978-3-031-53025-8http://hdl.handle.net/10198/30322This paper provides some comparisons of Automatic Speech Recognition (ASR) services for Portuguese that were developed in the scope of the Safe Cities project. ASR technology has enabled bi-directional voice-driven interfaces, and its demand in Portuguese is evident due to the language’s global prominence. However, the transcription process has complexities, and a high accuracy depends on the ability of capturing speech variability and language intricacies, while being rigorous in terms of semantics. The study first describes ASR services/models by Google, Microsoft, Amazon, IBM, and Voice Interaction regarding their main features. To compare them, three tests were proposed. Test A uses a small dataset with six audio recordings to evaluate in terms of word hit rate the accuracy of online services, with IBM outperforming others (pt-BR: 93.33%). Tests B and C utilize theMozilla Common Voice database filtered by a keywords’ set to compare online and offline models for Brazilian and European Portuguese regarding accuracy (Ratcliff-Obershelp algorithm), Word Error Rate, Match Error Rate, Word Information Loss, Character Error Rate and Response-Request Ratio. Test B highlights the higher accuracy of Google Cloud (pt-PT: 94.90%) and Azure (pt-BR: 98.11%). Test C showcases the potential of Voice Interaction’s real-time application despite its lower accuracy (pt-PT: 78.81%). The tests were carried out using a framework developed using Python 3.x on a Raspberry Pi 4 model B with a server desktop and the REST APIs from the companies’ repositories.engAutomatic Speech RecognitionPortugueseLanguage ModelTranscriptionMozilla Common VoiceASR accuracyconference paper10.1007/978-3-031-53025-8_16