Deep Neural Networks For Automatic Speech Processing: A Survey From Large Corpora To Limited Data

Abstract

Most state-of-the-art speech systems are using Deep Neural Networks (DNNs). Those systems require a large amount of data to be learned. Hence, learning state-of-the-art frameworks on under-resourced speech languages/problems is a difficult task. Problems could be the limited amount of data for impaired speech. Furthermore, acquiring more data and/or expertise is time-consuming and expensive. In this paper we position ourselves for the following speech processing tasks: Automatic Speech Recognition, speaker identification and emotion recognition. To assess the problem of limited data, we firstly investigate state-of-the-art Automatic Speech Recognition systems as it represents the hardest tasks (due to the large variability in each language). Next, we provide an overview of techniques and tasks requiring fewer data. In the last section we investigate few-shot techniques as we interpret under-resourced speech as a few-shot problem. In that sense we propose an overview of few-shot techniq

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyroger2020deep

Related papers

• Automatic Speech Recognition Using Advanced Deep Learning Approaches: A Survey (2024)16.63
• Deep Neural Network Techniques For Monaural Speech Enhancement: State Of The Art Analysis (2022)0.00
• Deep Learning For Distant Speech Recognition (2017)0.00
• Neural2speech: A Transfer Learning Framework For Neural-driven Speech Reconstruction (2023)5.24
• DNN Based Speaker Recognition On Short Utterances (2016)0.00
• A Network Of Deep Neural Networks For Distant Speech Recognition (2017)10.35
• Transfer Learning For Improving Speech Emotion Classification Accuracy (2018)15.10
• Almost Unsupervised Text To Speech And Automatic Speech Recognition (2019)0.00