I-Vector estimation as auxiliary task for Multi-Task Learning based acoustic modeling for automatic speech recognition.
Gueorgui PironkovStéphane DupontThierry DutoitPublished in: SLT (2016)
Keyphrases
- language model
- speech recognition
- automatic speech recognition
- multi task learning
- acoustic features
- multi task
- speech sounds
- speech signal
- multiple tasks
- learning tasks
- broadcast news
- speech retrieval
- learning problems
- gaussian processes
- conversational speech
- feature vectors
- transfer learning
- high order
- theoretical analysis
- multitask learning
- learning algorithm
- machine learning
- bayesian networks
- supervised learning