Deep Learning for Environmentally Robust Speech Recognition: An Overview of Recent Developments.
Zixing ZhangJürgen T. GeigerJouni PohjalainenAmr El-Desoky MousaWenyu JinBjörn W. SchullerPublished in: ACM Trans. Intell. Syst. Technol. (2018)
Keyphrases
- recent developments
- speech recognition
- deep learning
- noisy environments
- hidden markov models
- language model
- speech signal
- automatic speech recognition
- recent advances
- speech recognition systems
- speech recognizer
- speech synthesis
- speaker independent
- unsupervised learning
- pattern recognition
- speaker identification
- speech recognition technology
- partial occlusion
- machine learning
- natural images
- computer vision