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: CoRR (2022)
Keyphrases
- speech recognition
- hidden markov models
- speech synthesis
- speech processing
- language model
- keyword spotting
- noisy environments
- speech recognition systems
- pattern recognition
- automatic speech recognition
- speech signal
- speaker identification
- speech recognition technology
- human visual system
- speech retrieval
- speech understanding
- speech recognizers
- speaker dependent
- information retrieval
- speaker independent
- speech recognizer
- cepstral coefficients
- speech recognition errors
- handwriting recognition
- feature extraction