Evolved Speech-Transformer: Applying Neural Architecture Search to End-to-End Automatic Speech Recognition.
Jihwan KimJisung WangSangki KimYeha LeePublished in: INTERSPEECH (2020)
Keyphrases
- end to end
- automatic speech recognition
- neural architecture
- speech recognition
- speech signal
- word error rate
- broadcast news
- conversational speech
- hidden markov models
- speech corpus
- congestion control
- neural network
- acoustic features
- noisy environments
- language model
- spontaneous speech
- spoken words
- pattern recognition
- speech retrieval
- speech sounds
- visual features
- search space
- recognition errors
- image processing
- feed forward
- speech synthesis
- acoustic models
- real time