Improving Under-Resourced Code-Switched Speech Recognition: Large Pre-trained Models or Architectural Interventions.
Joshua Jansen van VürenThomas NieslerPublished in: INTERSPEECH (2023)
Keyphrases
- speech recognition
- pre trained
- hidden markov models
- speech synthesis
- language model
- neural network
- speech processing
- speech signal
- acoustic models
- probabilistic model
- noisy environments
- speaker identification
- speech recognition technology
- speaker dependent
- speech recognizer
- automatic speech recognition
- learning process
- face recognition