Incorporating L2 Phonemes Using Articulatory Features for Robust Speech Recognition.
Jisung WangHaram LeeMyungwoo OhPublished in: CoRR (2023)
Keyphrases
- speech recognition
- speech recognition systems
- noisy environments
- speech signal
- speech synthesis
- language model
- cepstral coefficients
- pattern recognition
- speech recognizer
- hidden markov models
- speech understanding
- speaker identification
- speech processing
- feature space
- automatic speech recognition
- speech recognition technology
- feature set
- feature vectors
- feature extraction
- speaker independent
- mel frequency cepstral coefficients
- machine learning
- isolated word
- extracted features
- digit recognition
- vocal tract
- extracting features
- speaker dependent
- computer vision
- neural network