Analyzing Phonetic and Graphemic Representations in End-to-End Automatic Speech Recognition.
Yonatan BelinkovAhmed AliJames R. GlassPublished in: CoRR (2019)
Keyphrases
- end to end
- automatic speech recognition
- speech recognition
- speech sounds
- speech signal
- hidden markov models
- broadcast news
- word error rate
- spoken term detection
- acoustic models
- conversational speech
- noisy environments
- spoken words
- pattern recognition
- speech retrieval
- language model
- speech recognizer
- recognition errors
- admission control
- speech corpus
- speaker adaptation
- speech synthesis
- spoken document retrieval
- speaker independent
- word recognition
- congestion control
- machine learning
- spontaneous speech
- internet protocol
- handwriting recognition
- word level
- speaker identification
- application layer
- neural network