K-Wav2vec 2.0: Automatic Speech Recognition based on Joint Decoding of Graphemes and Syllables.
Jounghee KimPilsung KangPublished in: INTERSPEECH (2022)
Keyphrases
- automatic speech recognition
- speech recognition
- speech signal
- word error rate
- hidden markov models
- conversational speech
- spoken words
- word recognition
- noisy environments
- speech retrieval
- broadcast news
- spontaneous speech
- recognition errors
- pattern recognition
- speech synthesis
- speech recognizer
- language model
- vocal tract
- acoustic features
- speech recognition systems
- speaker adaptation
- viterbi algorithm
- handwriting recognition
- discriminative training
- text to speech
- edge detection
- speech corpus
- speech sounds