Multimodal Fusion of Multirate Acoustic, Prosodic, and Lexical Speaker Characteristics for Native Language Identification.
Prashanth Gurunath ShivakumarSandeep Nallan ChakravarthulaPanayiotis G. GeorgiouPublished in: INTERSPEECH (2016)
Keyphrases
- language identification
- prosodic features
- speaker verification
- speaker identification
- multimodal fusion
- speech recognition
- audio visual
- document images
- machine learning
- text to speech
- wordnet
- multi modal
- noisy environments
- natural language processing
- hidden markov models
- synthesized speech
- web information retrieval
- probabilistic model
- high dimensional
- neural network