Comparison of Unsupervised Learning and Supervised Learning with Noisy Labels for Low-Resource Speech Recognition.
Yanick SchranerChristian SchellerMichel PlüssLukas NeukomManfred VogelPublished in: INTERSPEECH (2022)
Keyphrases
- speech recognition
- unsupervised learning
- supervised learning
- noisy environments
- training data
- hidden markov models
- training set
- automatic speech recognition
- speech signal
- speech recognizer
- semi supervised
- speech processing
- language model
- speech synthesis
- pattern recognition
- speech recognition systems
- machine learning
- semi supervised learning
- speech recognition technology
- handwriting recognition
- expectation maximization
- mixture model
- speech understanding
- dimensionality reduction
- active learning
- feature selection
- audio visual speech recognition
- keyword spotting
- speech retrieval
- speaker identification
- background noise
- unlabeled data
- labeled data
- model selection
- digit recognition
- text classification
- reinforcement learning
- learning algorithm
- probabilistic model
- speaker dependent
- feature space