iMetricGAN: Intelligibility Enhancement for Speech-in-Noise Using Generative Adversarial Network-Based Metric Learning.
Haoyu LiSzu-Wei FuYu TsaoJunichi YamagishiPublished in: INTERSPEECH (2020)
Keyphrases
- metric learning
- signal to noise ratio
- speech recognition
- distance metric
- distance metric learning
- machine learning and pattern recognition
- semi supervised
- pairwise
- learning tasks
- multi task
- dimensionality reduction
- distance function
- mahalanobis metric
- speech signal
- image processing
- semi supervised learning
- unsupervised learning
- feature space
- pattern recognition
- generative model
- input data
- image segmentation