ASAPP-ASR: Multistream CNN and Self-Attentive SRU for SOTA Speech Recognition.
Jing PanJoshua ShapiroJeremy WohlwendKyu J. HanTao LeiTao MaPublished in: CoRR (2020)
Keyphrases
- speech recognition
- automatic speech recognition
- hidden markov models
- speech signal
- speech synthesis
- speech recognizer
- language model
- word error rate
- speech retrieval
- noisy environments
- speech processing
- pattern recognition
- speech recognizers
- handwriting recognition
- speech understanding
- keyword spotting
- speaker identification
- speech recognition technology
- speech recognition systems
- broadcast news
- focus of attention
- acoustic features
- speaker diarization
- character recognition
- speaker independent
- acoustic models
- visual features
- neural network