LSTM time and frequency recurrence for automatic speech recognition.
Jinyu LiAbdelrahman MohamedGeoffrey ZweigYifan GongPublished in: ASRU (2015)
Keyphrases
- automatic speech recognition
- speech recognition
- hidden markov models
- speech signal
- word error rate
- conversational speech
- broadcast news
- speech corpus
- spoken words
- speech retrieval
- word recognition
- acoustic features
- spontaneous speech
- recognition errors
- recurrent neural networks
- machine learning
- noisy environments
- pattern recognition
- natural language
- computer vision