Yao-Hung Hubert Tsai

Yao-Hung Hubert Tsai

Auto-generated profile, based on publicly available information

Yao-Hung Hubert Tsai

Carnegie Mellon University

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 October 2021 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
WHWei-Ning Hsu
Wei-Ning Hsu
BBBenjamin Bolte
Benjamin Bolte
YTYao-Hung Hubert Tsai
Yao-Hung Hubert Tsai
KLKushal Lakhotia
Kushal Lakhotia
RSRuslan Salakhutdinov
Ruslan Salakhutdinov
AMAbdelrahman Mohamed
Abdelrahman Mohamed
Self-supervised approaches for speech representation learning are challenged by three unique problems: (1) there are multiple sound units in each input utterance, (2) there is no lexicon of input sound units during the pre-training phase, and (3) sound units have variable lengths with no explicit segmentation. To deal with these three problems, we propose the Hidden-Unit BERT (HuBERT) approach for self-supervised speech representation learning, which utilizes an offline clustering step to provide aligned target labels for a BERT-like prediction loss. A key ingredient of our approach is applying the prediction loss over the masked regions only, which forces the model to learn a combined acoustic and language model over the continuous inputs. HuBERT relies primarily on the consistency of the unsupervised clustering step rather than the intrinsic quality of the assigned cluster labels. Starting with a simple k-means teacher of 100 clusters, and using two iterations of clustering, the HuBERT model either matches or improves upon the state-of-the-art wav2vec 2.0 performance on the Librispeech (960h) and Libri-light (60,000h) benchmarks with 10min, 1h, 10h, 100h, and 960h fine-tuning subsets. Using a 1B parameter model, HuBERT shows up to 19% and 13% relative WER reduction on the more challenging dev-other and test-other evaluation subsets.

1 January 2019
Verified
Conference Paper
Open access
PDF file
YTYao-Hung Hubert Tsai
Yao-Hung Hubert Tsai
SBShaojie Bai
Shaojie Bai
PLPaul Pu Liang
Paul Pu Liang
JKJ. Zico Kolter
J. Zico Kolter
LMLouis-Philippe Morency
Louis-Philippe Morency
RSRuslan Salakhutdinov
Ruslan Salakhutdinov
Yao-Hung Hubert Tsai, Shaojie Bai, Paul Pu Liang, J. Zico Kolter, Louis-Philippe Morency, Ruslan Salakhutdinov. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 2019.

1 January 2020
Verified
Conference Paper
Open access
PDF file
YTYao-Hung Hubert Tsai
Yao-Hung Hubert Tsai
MMMartin Ma
Martin Ma
MYMuqiao Yang
Muqiao Yang
RSRuslan Salakhutdinov
Ruslan Salakhutdinov
LMLouis-Philippe Morency
Louis-Philippe Morency
Yao-Hung Hubert Tsai, Martin Ma, Muqiao Yang, Ruslan Salakhutdinov, Louis-Philippe Morency. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2020.

5 May 2022 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Verified
Journal Article
Closed access
YTYao-Hung Tsai
Yao-Hung Tsai
SLShen-Iuan Liu
Shen-Iuan Liu
A 12-bit 20-MS/s asynchronous successive approximation register (SAR) analog-to-digital converter (ADC) is presented by using the digital place-and-route (DPR) tools. The macrocells for the capacitive digital-to-analog converter, the bootstrapped switch, and the dynamic comparator are presented. The custom standard cells for the dynamic SAR logic are also presented. By using the macrocells and the custom standard ones, the layout of this SAR ADC is completed by using the DPR tools. Several techniques are presented to improve the parasitic capacitances, the current density of the metal interconnections, and the nonideal effects caused by the DPR tools. This SAR ADC is fabricated in 40-nm CMOS technology and its active area is 0.0067 mm 2 . To compare with the full-custom method, the proposed DPR flow has speeded up by a factor of 288 to complete the interconnection wires. Its power dissipation is 363 $\mu \text{W}$ at 20 MS/s and the calculated Walden FoM is 23 fJ/c. step at Nyquist frequency.

14 May 2019 in arXiv
Verified
Preprint
Open access
PDF file
YTYao-Hung Hubert Tsai
Yao-Hung Hubert Tsai
PLPaul Pu Liang
Paul Pu Liang
AZAmir Zadeh
Amir Zadeh
LMLouis-Philippe Morency
Louis-Philippe Morency
RSRuslan Salakhutdinov
Ruslan Salakhutdinov
Learning multimodal representations is a fundamentally complex research problem due to the presence of multiple heterogeneous sources of information. Although the presence of multiple modalities provides additional valuable information, there are two key challenges to address when learning from multimodal data: 1) models must learn the complex intra-modal and cross-modal interactions for prediction and 2) models must be robust to unexpected missing or noisy modalities during testing. In this paper, we propose to optimize for a joint generative-discriminative objective across multimodal data and labels. We introduce a model that factorizes representations into two sets of independent factors: multimodal discriminative and modality-specific generative factors. Multimodal discriminative factors are shared across all modalities and contain joint multimodal features required for discriminative tasks such as sentiment prediction. Modality-specific generative factors are unique for each modality and contain the information required for generating data. Experimental results show that our model is able to learn meaningful multimodal representations that achieve state-of-the-art or competitive performance on six multimodal datasets. Our model demonstrates flexible generative capabilities by conditioning on independent factors and can reconstruct missing modalities without significantly impacting performance. Lastly, we interpret our factorized representations to understand the interactions that influence multimodal learning.

11 November 2019 in arXiv
Verified
Preprint
Open access
PDF file
YTYao-Hung Hubert Tsai
Yao-Hung Hubert Tsai
SBShaojie Bai
Shaojie Bai
MYMakoto Yamada
Makoto Yamada
LMLouis-Philippe Morency
Louis-Philippe Morency
RSRuslan Salakhutdinov
Ruslan Salakhutdinov
Transformer is a powerful architecture that achieves superior performance on various sequence learning tasks, including neural machine translation, language understanding, and sequence prediction. At the core of the Transformer is the attention mechanism, which concurrently processes all inputs in the streams. In this paper, we present a new formulation of attention via the lens of the kernel. To be more precise, we realize that the attention can be seen as applying kernel smoother over the inputs with the kernel scores being the similarities between inputs. This new formulation gives us a better way to understand individual components of the Transformer's attention, such as the better way to integrate the positional embedding. Another important advantage of our kernel-based formulation is that it paves the way to a larger space of composing Transformer's attention. As an example, we propose a new variant of Transformer's attention which models the input as a product of symmetric kernels. This approach achieves competitive performance to the current state of the art model with less computation. In our experiments, we empirically study different kernel construction strategies on two widely used tasks: neural machine translation and sequence prediction.