Performance vs. hardware requirements in state-of-the-art automatic speech recognition

The last decade brought significant advances in automatic speech recognition (ASR) thanks to the evolution of deep learning methods. ASR systems evolved from pipeline-based systems, that modeled hand-crafted speech features with probabilistic frameworks and generated phone posteriors, to end-to-end...

Full description

Saved in:
Bibliographic Details
Published in:EURASIP journal on audio, speech, and music processing speech, and music processing, 2021-07, Vol.2021 (1), p.1-30, Article 28
Main Authors: Georgescu, Alexandru-Lucian, Pappalardo, Alessandro, Cucu, Horia, Blott, Michaela
Format: Article
Language:English
Subjects:
Acoustics
Artificial neural networks
Automatic speech recognition
Deep learning
End-to-end ASR systems
Engineering
Engineering Acoustics
Evolution
Hardware
Machine learning
Mathematics in Music
Performance analysis
Review
Signal,Image and Speech Processing
Speech recognition
Survey
Tradeoffs
Transcription
Voice recognition
Waveforms
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The last decade brought significant advances in automatic speech recognition (ASR) thanks to the evolution of deep learning methods. ASR systems evolved from pipeline-based systems, that modeled hand-crafted speech features with probabilistic frameworks and generated phone posteriors, to end-to-end (E2E) systems, that translate the raw waveform directly into words using one deep neural network (DNN). The transcription accuracy greatly increased, leading to ASR technology being integrated into many commercial applications. However, few of the existing ASR technologies are suitable for integration in embedded applications, due to their hard constrains related to computing power and memory usage. This overview paper serves as a guided tour through the recent literature on speech recognition and compares the most popular ASR implementations. The comparison emphasizes the trade-off between ASR performance and hardware requirements, to further serve decision makers in choosing the system which fits best their embedded application. To the best of our knowledge, this is the first study to provide this kind of trade-off analysis for state-of-the-art ASR systems.
ISSN:1687-4722
1687-4714
1687-4722
DOI:10.1186/s13636-021-00217-4