Variable Attention Masking for Configurable Transformer Transducer Speech Recognition.
Pawel SwietojanskiStefan BraunDogan CanThiago Fraga da SilvaArnab GhoshalTakaaki HoriRoger HsiaoHenry MasonErik McDermottHonza SilovskyRuchir TravadiXiaodan ZhuangPublished in: ICASSP (2023)
Keyphrases
- speech recognition
- automatic speech recognition
- hidden markov models
- speech synthesis
- language model
- speech processing
- speech understanding
- speech signal
- speech recognizer
- pattern recognition
- noisy environments
- handwriting recognition
- speech recognition systems
- speech recognition technology
- speaker identification
- speech retrieval
- neural network
- speech recognizers
- isolated word
- cepstral coefficients
- acoustic models
- keyword spotting
- human visual system
- computer vision