Says Who? Deep Learning Models for Joint Speech Recognition, Segmentation and Diarization.
Amitrajit SarkarSurajit DasguptaSudip Kumar NaskarSivaji BandyopadhyayPublished in: ICASSP (2018)
Keyphrases
- speech recognition
- learning models
- speaker identification
- hidden markov models
- speaker diarization
- machine learning
- learning algorithm
- level set
- speech synthesis
- language model
- loss function
- conditional random fields
- segmentation algorithm
- speech signal
- pattern recognition
- speech recognizer
- image segmentation
- learning tasks
- machine learning algorithms
- automatic speech recognition
- speech recognition systems
- noisy environments
- semi supervised learning
- learning problems
- handwriting recognition
- classification models
- segmentation method
- neural network
- speaker independent
- supervised learning
- computer vision
- energy function
- natural language
- bayesian networks