28 citations · 109 across the 36 of their papers we have counts for
6 papers · 1 filter
Interrupted and cascaded permutation invariant training for speech separation
Gene-Ping Yang, Szu-Lin Wu, Yao-Wen Mao +2
Permutation Invariant Training (PIT) has long been a stepping stone method for training speech separation model in handling the label ambiguity problem. With PIT selecting the mini…
Sequence-to-sequence Automatic Speech Recognition with Word Embedding Regularization and Fused Decoding
Alexander H. Liu, Tzu-Wei Sung, Shun-Po Chuang +2
In this paper, we investigate the benefit that off-the-shelf word embedding can bring to the sequence-to-sequence (seq-to-seq) automatic speech recognition (ASR). We first introduc…
Towards Unsupervised Speech Recognition and Synthesis with Quantized Speech Representation Learning
Alexander H. Liu, Tao Tu, Hung-yi Lee +1
In this paper we propose a Sequential Representation Quantization AutoEncoder (SeqRQ-AE) to learn from primarily unpaired audio data and produce sequences of representations very c…
Improved Speech Separation with Time-and-Frequency Cross-domain Joint Embedding and Clustering
Gene-Ping Yang, Chao-I Tuan, Hung-Yi Lee +1
Speech separation has been very successful with deep learning techniques. Substantial effort has been reported based on approaches over spectrogram, which is well known as the stan…
From Semi-supervised to Almost-unsupervised Speech Recognition with Very-low Resource by Jointly Learning Phonetic Structures from Audio and Text Embeddings
Yi-Chen Chen, Sung-Feng Huang, Hung-yi Lee +1
Producing a large amount of annotated speech data for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced. However, we…
Completely Unsupervised Speech Recognition By A Generative Adversarial Network Harmonized With Iteratively Refined Hidden Markov Models
Kuan-Yu Chen, Che-Ping Tsai, Da-Rong Liu +2
Producing a large annotated speech corpus for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced, but collecting a rel…