Domain Adaptation Speech-to-Text for Low-Resource European Portuguese Using Deep Learning
Eduardo Medeiros (),
Leonel Corado,
Luís Rato (),
Paulo Quaresma and
Pedro Salgueiro
Additional contact information
Eduardo Medeiros: Escola de Ciências e Tecnologia, Universidade de Évora, 7000-671 Évora, Portugal
Leonel Corado: Escola de Ciências e Tecnologia, Universidade de Évora, 7000-671 Évora, Portugal
Luís Rato: Escola de Ciências e Tecnologia, Universidade de Évora, 7000-671 Évora, Portugal
Paulo Quaresma: Escola de Ciências e Tecnologia, Universidade de Évora, 7000-671 Évora, Portugal
Pedro Salgueiro: Escola de Ciências e Tecnologia, Universidade de Évora, 7000-671 Évora, Portugal
Future Internet, 2023, vol. 15, issue 5, 1-16
Abstract:
Automatic speech recognition (ASR), commonly known as speech-to-text, is the process of transcribing audio recordings into text, i.e., transforming speech into the respective sequence of words. This paper presents a deep learning ASR system optimization and evaluation for the European Portuguese language. We present a pipeline composed of several stages for data acquisition, analysis, pre-processing, model creation, and evaluation. A transfer learning approach is proposed considering an English language-optimized model as starting point; a target composed of European Portuguese; and the contribution to the transfer process by a source from a different domain consisting of a multiple-variant Portuguese language dataset, essentially composed of Brazilian Portuguese. A domain adaptation was investigated between European Portuguese and mixed (mostly Brazilian) Portuguese. The proposed optimization evaluation used the NVIDIA NeMo framework implementing the QuartzNet15×5 architecture based on 1D time-channel separable convolutions. Following this transfer learning data-centric approach, the model was optimized, achieving a state-of-the-art word error rate (WER) of 0.0503.
Keywords: machine learning; deep learning; deep neural networks; speech-to-text; automatic speech recognition; NVIDIA NeMo; GPUs; data-centric; Portuguese language (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2023
References: View complete reference list from CitEc
Citations:
Downloads: (external link)
https://www.mdpi.com/1999-5903/15/5/159/pdf (application/pdf)
https://www.mdpi.com/1999-5903/15/5/159/ (text/html)
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:gam:jftint:v:15:y:2023:i:5:p:159-:d:1131293
Access Statistics for this article
Future Internet is currently edited by Ms. Grace You
More articles in Future Internet from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().