K-Wav2vec 2.0: Automatic Speech Recognition based on Joint Decoding of Graphemes and Syllables.
Jounghee KimPilsung KangPublished in: CoRR (2021)
Keyphrases
- automatic speech recognition
- speech recognition
- speech signal
- hidden markov models
- word error rate
- broadcast news
- noisy environments
- spoken words
- language model
- conversational speech
- speech retrieval
- pattern recognition
- word recognition
- recognition errors
- speech synthesis
- speech corpus
- non stationary
- acoustic features
- spontaneous speech
- viterbi algorithm
- handwriting recognition
- discriminative training
- speech recognition systems
- error rate
- image processing
- vocal tract
- neural network
- feature extraction
- speech sounds