Incorporating L2 Phonemes Using Articulatory Features for Robust Speech Recognition.
Jisung WangHaram LeeMyungwoo OhPublished in: INTERSPEECH (2023)
Keyphrases
- speech recognition
- speech recognition systems
- speech synthesis
- speech signal
- hidden markov models
- noisy environments
- automatic speech recognition
- cepstral coefficients
- speech understanding
- language model
- pattern recognition
- speaker identification
- speech recognizer
- feature space
- speech processing
- feature set
- speech recognition technology
- mel frequency cepstral coefficients
- speaker independent
- vocal tract
- feature extraction
- speech recognizers
- information retrieval
- keyword spotting
- speaker recognition
- feature vectors
- visual speech recognition
- extracting features
- speech recognition errors
- low level