Alexander H. Liu

Lin-Shan Lee, Hung-yi Lee, Alexander H. Liu, 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Sequence-to-Sequence Automatic Speech Recognition with Word Embedding Regularization and Fused Decoding

Hung-yi Lee, Alexander H. Liu, Lin-shan Lee, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Cross-Modal Discrete Representation Learning pdf

James Glass, James R. Glass, Aude Oliva, 2021, ACL.

On the Interplay Between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesis pdf

James Glass, Junichi Yamagishi, Shiyu Chang, 2021, ArXiv.

PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition pdf

James Glass, Shiyu Chang, Yang Zhang, 2021, ArXiv.

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

Lin-Shan Lee, Hung-yi Lee, Alexander H. Liu, 2020, 2021 IEEE Spoken Language Technology Workshop (SLT).

Towards End-to-End Unsupervised Speech Recognition

Alexander H. Liu, Michael Auli, Wei-Ning Hsu, 2022, 2022 IEEE Spoken Language Technology Workshop (SLT).

UAVM: A Unified Model for Audio-Visual Learning

Alexander H. Liu, Yuan Gong, Andrew Rouditchenko, 2022, ArXiv.

Contrastive Audio-Visual Masked Autoencoder

James R. Glass, Alexander H. Liu, David F. Harwath, 2022, ArXiv.

UAVM: Towards Unifying Audio and Visual Models

Alexander H. Liu, Yuan Gong, Andrew Rouditchenko, 2022, IEEE Signal Processing Letters.

PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition

James R. Glass, Alexander H. Liu, Shiyu Chang, 2021, NeurIPS.

UAVM: Towards Unifying Audio and Visual Models

Alexander H. Liu, Yuan Gong, Andrew Rouditchenko, 2022, IEEE Signal Processing Letters.

Contrastive Audio-Visual Masked Autoencoder

James R. Glass, Alexander H. Liu, David F. Harwath, 2022, ICLR.

Listen, Think, and Understand

Alexander H. Liu, Yuan Gong, Hongyin Luo, 2023, ArXiv.

Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant Clustering

Alexander H. Liu, Heng-Jui Chang, James Glass, 2023, INTERSPEECH 2023.

Simple and Effective Unsupervised Speech Synthesis

James R. Glass, Alexander H. Liu, Michael Auli, 2022, INTERSPEECH.

Sequence-to-Sequence Automatic Speech Recognition with Word Embedding Regularization and Fused Decoding

Alexander H. Liu, Hung-yi Lee, Lin-Shan Lee, 2019, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Towards Unsupervised Speech Recognition and Synthesis with Quantized Speech Representation Learning

Alexander H. Liu, Hung-yi Lee, Lin-Shan Lee, 2019, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning

James R. Glass, Alexander H. Liu, Michael Auli, 2023, ArXiv.

Masked Autoencoders As The Unified Learners For Pre-Trained Sentence Representation

Alexander H. Liu, Samuel J. Yang, 2022, ArXiv.

Worse WER, but Better BLEU? Leveraging Word Embedding as Intermediate in Multitask End-to-End Speech Translation

Alexander H. Liu, Hung-yi Lee, Shun-Po Chuang, 2020, ACL.

Routing with Self-Attention for Multimodal Capsule Networks pdf

James Glass, Mubarak Shah, James R. Glass, 2021, ArXiv.

Semi-supervised Learning for Multi-speaker Text-to-speech Synthesis Using Discrete Speech Representation

Alexander H. Liu, Hung-yi Lee, Tao Tu, 2020, INTERSPEECH.

Listen, Think, and Understand

Alexander H. Liu, Yuan Gong, Hongyin Luo, 2023, ArXiv.