DEFORMER: Coupling Deformed Localized Patterns with Global Context for Robust End-to-end Speech Recognition.
Jiamin XieJohn H. L. HansenPublished in: INTERSPEECH (2022)
Keyphrases
- end to end
- speech recognition
- global context
- noisy environments
- hidden markov models
- language model
- automatic speech recognition
- pattern recognition
- speech synthesis
- speech recognizer
- speech signal
- congestion control
- text localization and recognition
- speech recognition systems
- speaker identification
- global information
- feature descriptors
- multiresolution
- information retrieval