The Performance Evaluation of Attention-Based Neural ASR under Mixed Speech Input.
Bradley HeMartin RadfarPublished in: CoRR (2021)
Keyphrases
- automatic speech recognition
- speech recognition
- speech signal
- word error rate
- spontaneous speech
- noisy environments
- broadcast news
- neural network
- spoken words
- speech corpus
- network architecture
- focus of attention
- visual attention
- text input
- pattern recognition
- speech synthesis
- information retrieval
- autistic children
- video sequences
- recognition errors
- finite state transducers
- input data
- visual input
- speaker identification
- visual information
- language acquisition
- audio visual