Training the pronunciation of L2 vowels under different conditions: the use of non-lexical materials and masking noise.
Joan C. MoraMireia OrtegaIngrid Mora-PlazaCristina Aliaga-GarcíaPublished in: Phonetica (2022)
Keyphrases
- speech recognition
- sufficient conditions
- noisy environments
- random noise
- training and testing data
- noise level
- context sensitive
- training process
- noisy data
- acoustic models
- supervised learning
- hidden markov models
- training set
- probabilistic model
- machine learning
- speech recognition systems
- automatic speech recognition
- cross correlation
- empirically derived
- human visual system
- word sense disambiguation
- semantic network
- signal to noise ratio
- learning materials
- training samples
- learning styles
- domain specific
- natural language processing
- artificial neural networks
- training data