Explicit Alignment of Text and Speech Encodings for Attention-Based End-to-End Speech Recognition.
Jennifer DrexlerJames R. GlassPublished in: ASRU (2019)
Keyphrases
- end to end
- speech recognition
- speech synthesis
- speech signal
- automatic speech recognition
- language model
- hidden markov models
- speech recognizer
- speech processing
- pattern recognition
- information retrieval
- text to speech
- speech recognition technology
- speaker independent
- noisy environments
- speech recognition systems
- speaker identification
- speech recognizers
- neural network
- recognition engine
- keyword spotting
- cepstral coefficients
- speaker dependent
- speech recognition errors
- speaker diarization
- document analysis
- speech retrieval
- news video
- handwriting recognition