A Fast-Converged Acoustic Modeling for Korean Speech Recognition: A Preliminary Study on Time Delay Neural Network.
Hosung ParkDonghyun LeeMinkyu LimYoseb KangJuneseok OhJi-Hwan KimPublished in: CoRR (2018)
Keyphrases
- speech recognition
- speech recognition systems
- speech recognizers
- speaker independent
- acoustic models
- hidden markov models
- pattern recognition
- language model
- automatic speech recognition
- speech synthesis
- speaker identification
- speech recognizer
- noisy environments
- speech signal
- speech recognition technology
- speech understanding
- speech processing
- speaker dependent
- noisy speech
- information retrieval
- speech recognition errors
- acoustic features
- speaker recognition
- speech retrieval
- feature extraction
- image processing