WaveNet With Cross-Attention for Audiovisual Speech Recognition.
Hui WangFei GaoYue ZhaoLicheng WuPublished in: IEEE Access (2020)
Keyphrases
- speech recognition
- hidden markov models
- language model
- automatic speech recognition
- speech signal
- speech understanding
- speech recognizer
- pattern recognition
- speech recognition technology
- speech processing
- speech recognition systems
- speech synthesis
- noisy environments
- keyword spotting
- audio visual
- speaker identification
- speech recognition errors
- visual information
- cepstral coefficients
- information retrieval
- neural network
- isolated word
- speaker dependent
- multimedia content
- mixture model
- machine learning