Speech (3/1/2022)
Lecture: (by Shinji Watanabe)
- What is speech?
- Speech applications
- Speech databases
- Speech hierarchy
Language in 10: Javanese
Slides: Speech
Discussion: No discussion, but the introduction of assignment 3.
References:
- Reference: Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning (Kim et al. 2016)
- Reference: wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations (Baevski et al. 2020)
- Reference: HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units (Hsu et al. 2021)
- Reference: An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition (Chang et al. 2021)
- Tutorial: ESPnet2 Tutorial