activity
20152021
most citedImproved Speech Separation with Time-and-Frequency Cross-domain Joint Embedding and Clustering

3 citations · 11 across the 12 of their papers we have counts for

collaborators

26 papers

cs.CL2021

Towards Lifelong Learning of End-to-end ASR

Heng-Jui Chang, Hung-yi Lee, Lin-shan Lee

Automatic speech recognition (ASR) technologies today are primarily optimized for given datasets; thus, any changes in the application environment (e.g., acoustic conditions or top…

cs.CL2020

End-to-end Whispered Speech Recognition with Frequency-weighted Approaches and Pseudo Whisper Pre-training

Heng-Jui Chang, Alexander H. Liu, Hung-yi Lee +1

Whispering is an important mode of human speech, but no end-to-end recognition results for it were reported yet, probably due to the scarcity of available whispered speech data. In…

cs.SD20193 cited

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…

cs.CL2019

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…

cs.CL20191 cited

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…

cs.SD20193 cited

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…