Deep Representation Learning In Speech Processing: Challenges, Recent Advances, And Future Trends

Abstract

Research on speech processing has traditionally considered the task of designing hand-engineered acoustic features (feature engineering) as a separate distinct problem from the task of designing efficient machine learning (ML) models to make prediction and classification decisions. There are two main drawbacks to this approach: firstly, the feature engineering being manual is cumbersome and requires human knowledge; and secondly, the designed features might not be best for the objective at hand. This has motivated the adoption of a recent trend in speech community towards utilisation of representation learning techniques, which can learn an intermediate representation of the input signal automatically that better suits the task at hand and hence lead to improved performance. The significance of representation learning has increased with advances in deep learning (DL), where the representations are more useful and less dependent on human knowledge, making it very conducive for tasks lik

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylatif2020deep

Related papers

• Automatic Speech Recognition Using Advanced Deep Learning Approaches: A Survey (2024)16.63
• Overview Of Speaker Modeling And Its Applications: From The Lens Of Deep Speaker Representation Learning (2024)10.74
• Deep Learning For Distant Speech Recognition (2017)0.00
• Speaker Recognition Based On Deep Learning: An Overview (2020)18.86
• An Unsupervised Autoregressive Model For Speech Representation Learning (2019)17.26
• Learning Disentangled Speech Representations (2023)0.00
• Visualizing Automatic Speech Recognition -- Means For A Better Understanding? (2022)4.52
• Bridging The Gap: Using Deep Acoustic Representations To Learn Grounded Language From Percepts And Raw Speech (2021)0.00