According to our database1, Sung-Feng Huang authored at least 11 papers between 2018 and 2021.
Legend:Book In proceedings Article PhD thesis Other
Non-autoregressive Mandarin-English Code-switching Speech Recognition with Pinyin Mask-CTC and Word Embedding Regularization.
Self-supervised Pre-training Reduces Label Permutation Instability of Speech Separation.
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, 2020
Audio Word2vec: Sequence-to-Sequence Autoencoding for Unsupervised Learning of Audio Segmentation and Representation.
IEEE ACM Trans. Audio Speech Lang. Process., 2019
From Semi-supervised to Almost-unsupervised Speech Recognition with Very-low Resource by Jointly Learning Phonetic Structures from Audio and Text Embeddings.
Improved Audio Embeddings by Adjacency-Based Clustering with Applications in Spoken Term Detection.
Almost-unsupervised Speech Recognition with Close-to-zero Resource Based on Phonetic Structures Learned from Very Small Unpaired Speech and Text Data.
Towards Unsupervised Automatic Speech Recognition Trained by Unaligned Speech and Text only.
Phonetic-and-Semantic Embedding of Spoken words with Applications in Spoken Content Retrieval.
Proceedings of the 2018 IEEE Spoken Language Technology Workshop, 2018