SAN-M: Memory Equipped Self-Attention for End-to-End Speech Recognition.
Zhifu GaoShiliang ZhangMing LeiIan McLoughlinPublished in: INTERSPEECH (2020)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- speech processing
- automatic speech recognition
- speech signal
- speech recognizer
- language model
- speaker identification
- pattern recognition
- speech synthesis
- congestion control
- speech recognition technology
- speech recognition systems
- noisy environments
- speech recognizers
- speaker independent
- speech retrieval
- high bandwidth
- speaker diarization
- isolated word
- signal processing
- computational complexity