Cross-Lingual Subspace Gaussian Mixture Models for Low-Resource Speech Recognition.
Liang LuArnab GhoshalSteve RenalsPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2014)
Keyphrases
- speech recognition
- cross lingual
- gaussian mixture model
- language modeling
- language model
- mixture model
- speaker recognition
- speaker identification
- feature space
- machine translation
- language independent
- hidden markov models
- cross language
- speech signal
- mel frequency cepstral coefficients
- em algorithm
- feature vectors
- expectation maximization
- n gram
- text classification
- maximum likelihood
- automatic speech recognition
- pattern recognition
- noisy environments
- test collection
- high dimensional
- news articles
- probabilistic model
- parallel corpora
- dimensionality reduction
- transfer learning
- retrieval model
- low dimensional
- query expansion
- word segmentation
- feature extraction
- computer vision
- feature selection
- document clustering
- model selection