Improving Multimodal Speech Recognition by Data Augmentation and Speech Representations.
Dan OneataHoria CucuPublished in: CVPR Workshops (2022)
Keyphrases
- speech recognition
- speech recognizer
- language model
- speech signal
- hidden markov models
- speech synthesis
- speech processing
- noisy environments
- automatic speech recognition
- computer vision
- multi modal
- noise reduction
- spoken language
- speaker identification
- speaker recognition
- natural language
- pattern recognition
- machine learning
- recognition engine
- speech recognition systems
- speech recognition errors
- speech retrieval