Journal
KNOWLEDGE-BASED SYSTEMS
Volume 277, Issue -, Pages -Publisher
ELSEVIER
DOI: 10.1016/j.knosys.2023.110851
Keywords
Automatic speech recognition; Deep transfer learning; Fine-tuning; Domain adaptation; Models fusion; Large language model; semantic knowledge. Acoustic model (AM) processing includes
Categories
Ask authors/readers for more resources
The combination of deep learning and automatic speech recognition has become an important challenge. This paper investigates DTL-based ASR frameworks and analyzes their limitations and advantages, providing opportunities for future research.
Automatic speech recognition (ASR) has recently become an important challenge when using deep learning (DL). It requires large-scale training datasets and high computational and storage resources. Moreover, DL techniques and machine learning (ML) approaches in general, hypothesize that training and testing data come from the same domain, with the same input feature space and data distribution characteristics. This assumption, however, is not applicable in some real-world artificial intelligence (AI) applications. Moreover, there are situations where gathering real data is challenging, expensive, or rarely occurring, which cannot meet the data requirements of DL models. deep transfer learning (DTL) has been introduced to overcome these issues, which helps develop high-performing models using real datasets that are small or slightly different but related to the training data. This paper presents a comprehensive survey of DTL-based ASR frameworks to shed light on the latest developments and helps academics and professionals understand current challenges. Specifically, after presenting the DTL background, a well-designed taxonomy is adopted to inform the state-of-the-art. A critical analysis is then conducted to identify the limitations and advantages of each framework. Moving on, a comparative study is introduced to highlight the current challenges before deriving opportunities for future research.(c) 2023 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available