Search

Your search keyword '"Hu, Ting"' showing total 5,035 results
Start Over Author "Hu, Ting"
5,035 results on '"Hu, Ting"'

653. 4 × 53 Gbit/s Electro-Optic Engine With a Surface-Normal Electroabsorption Modulator Array

Author

Grillanda, Stefano, primary, Tran, Cuong, additional, Che, Di, additional, Hu, Ting-Chen, additional, Basavanhally, Nagesh, additional, Papazian, Rick, additional, Kopf, Rose, additional, Tate, Alaric, additional, Cappuzzo, Mark, additional, Earnshaw, Mark, additional, Kim, K. W., additional, Raybon, Gregory, additional, Neilson, David, additional, and Iannone, Patrick, additional

Published
2023
Full Text
View/download PDF

668. The PRMT6/PARP1/CRL4B Complex Regulates the Circadian Clock and Promotes Breast Tumorigenesis

Author

Yang, Tianshu, primary, Huang, Wei, additional, Ma, Tianyu, additional, Yin, Xin, additional, Zhang, Jingyao, additional, Huo, Miaomiao, additional, Hu, Ting, additional, Gao, Tianyang, additional, Liu, Wei, additional, Zhang, Die, additional, Yu, Hefen, additional, Teng, Xu, additional, Zhang, Min, additional, Qin, Hao, additional, Yang, Yunkai, additional, Yuan, Baowen, additional, and Wang, Yan, additional

Published
2023
Full Text
View/download PDF

672. First-pass effect in patients with acute basilar artery occlusions undergoing stent retriever thrombectomy

Author

Zhao, Chenhao, primary, Hu, Ting, additional, Kong, Weilin, additional, Yang, De, additional, Wan, Junfang, additional, Lv, Kefeng, additional, Liao, Jiasheng, additional, Chen, Zhao, additional, Jiang, He, additional, Wu, Deping, additional, Yang, Ping, additional, Zi, Wenjie, additional, Li, Fengli, additional, and Yang, Qingwu, additional

Published
2023
Full Text
View/download PDF

692. Text is All You Need: Personalizing ASR Models using Controllable Speech Synthesis

Author

Yang, Karren, Hu, Ting-Yao, Chang, Jen-Hao Rick, Koppula, Hema Swetha, Tuzel, Oncel, Yang, Karren, Hu, Ting-Yao, Chang, Jen-Hao Rick, Koppula, Hema Swetha, and Tuzel, Oncel

Abstract

Adapting generic speech recognition models to specific individuals is a challenging problem due to the scarcity of personalized data. Recent works have proposed boosting the amount of training data using personalized text-to-speech synthesis. Here, we ask two fundamental questions about this strategy: when is synthetic data effective for personalization, and why is it effective in those cases? To address the first question, we adapt a state-of-the-art automatic speech recognition (ASR) model to target speakers from four benchmark datasets representative of different speaker types. We show that ASR personalization with synthetic data is effective in all cases, but particularly when (i) the target speaker is underrepresented in the global data, and (ii) the capacity of the global model is limited. To address the second question of why personalized synthetic data is effective, we use controllable speech synthesis to generate speech with varied styles and content. Surprisingly, we find that the text content of the synthetic data, rather than style, is important for speaker adaptation. These results lead us to propose a data selection strategy for ASR personalization based on speech content., Comment: ICASSP 2023

Published
2023

693. Corpus Synthesis for Zero-shot ASR domain Adaptation using Large Language Models

Author

Su, Hsuan, Hu, Ting-Yao, Koppula, Hema Swetha, Vemulapalli, Raviteja, Chang, Jen-Hao Rick, Yang, Karren, Mantena, Gautam Varma, Tuzel, Oncel, Su, Hsuan, Hu, Ting-Yao, Koppula, Hema Swetha, Vemulapalli, Raviteja, Chang, Jen-Hao Rick, Yang, Karren, Mantena, Gautam Varma, and Tuzel, Oncel

Abstract

While Automatic Speech Recognition (ASR) systems are widely used in many real-world applications, they often do not generalize well to new domains and need to be finetuned on data from these domains. However, target-domain data usually are not readily available in many scenarios. In this paper, we propose a new strategy for adapting ASR models to new target domains without any text or speech from those domains. To accomplish this, we propose a novel data synthesis pipeline that uses a Large Language Model (LLM) to generate a target domain text corpus, and a state-of-the-art controllable speech synthesis model to generate the corresponding speech. We propose a simple yet effective in-context instruction finetuning strategy to increase the effectiveness of LLM in generating text corpora for new domains. Experiments on the SLURP dataset show that the proposed method achieves an average relative word error rate improvement of $28\%$ on unseen target domains without any performance drop in source domains.

Published
2023

694. Scaled Prompt-Tuning for Few-Shot Natural Language Generation

Author

Hu, Ting, Meinel, Christoph, Yang, Haojin, Hu, Ting, Meinel, Christoph, and Yang, Haojin

Abstract

The increasingly Large Language Models (LLMs) demonstrate stronger language understanding and generation capabilities, while the memory demand and computation cost of fine-tuning LLMs on downstream tasks are non-negligible. Besides, fine-tuning generally requires a certain amount of data from individual tasks whilst data collection cost is another issue to consider in real-world applications. In this work, we focus on Parameter-Efficient Fine-Tuning (PEFT) methods for few-shot Natural Language Generation (NLG), which freeze most parameters in LLMs and tune a small subset of parameters in few-shot cases so that memory footprint, training cost, and labeling cost are reduced while maintaining or even improving the performance. We propose a Scaled Prompt-Tuning (SPT) method which surpasses conventional PT with better performance and generalization ability but without an obvious increase in training cost. Further study on intermediate SPT suggests the superior transferability of SPT in few-shot scenarios, providing a recipe for data-deficient and computation-limited circumstances. Moreover, a comprehensive comparison of existing PEFT methods reveals that certain approaches exhibiting decent performance with modest training cost such as Prefix-Tuning in prior study could struggle in few-shot NLG tasks, especially on challenging datasets.

Published
2023

695. Genetic heterogeneity analysis using genetic algorithm and network science

Author

Sha, Zhendong, Chen, Yuanzhu, Hu, Ting, Sha, Zhendong, Chen, Yuanzhu, and Hu, Ting

Abstract

Through genome-wide association studies (GWAS), disease susceptible genetic variables can be identified by comparing the genetic data of individuals with and without a specific disease. However, the discovery of these associations poses a significant challenge due to genetic heterogeneity and feature interactions. Genetic variables intertwined with these effects often exhibit lower effect-size, and thus can be difficult to be detected using machine learning feature selection methods. To address these challenges, this paper introduces a novel feature selection mechanism for GWAS, named Feature Co-selection Network (FCSNet). FCS-Net is designed to extract heterogeneous subsets of genetic variables from a network constructed from multiple independent feature selection runs based on a genetic algorithm (GA), an evolutionary learning algorithm. We employ a non-linear machine learning algorithm to detect feature interaction. We introduce the Community Risk Score (CRS), a synthetic feature designed to quantify the collective disease association of each variable subset. Our experiment showcases the effectiveness of the utilized GA-based feature selection method in identifying feature interactions through synthetic data analysis. Furthermore, we apply our novel approach to a case-control colorectal cancer GWAS dataset. The resulting synthetic features are then used to explain the genetic heterogeneity in an additional case-only GWAS dataset.

Published
2023

696. How complex is the microarray dataset? A novel data complexity metric for biological high-dimensional microarray data

Author

Sha, Zhendong, Zhu, Li, Jiang, Zijun, Chen, Yuanzhu, Hu, Ting, Sha, Zhendong, Zhu, Li, Jiang, Zijun, Chen, Yuanzhu, and Hu, Ting

Abstract

Data complexity analysis quantifies the hardness of constructing a predictive model on a given dataset. However, the effectiveness of existing data complexity measures can be challenged by the existence of irrelevant features and feature interactions in biological micro-array data. We propose a novel data complexity measure, depth, that leverages an evolutionary inspired feature selection algorithm to quantify the complexity of micro-array data. By examining feature subsets of varying sizes, the approach offers a novel perspective on data complexity analysis. Unlike traditional metrics, depth is robust to irrelevant features and effectively captures complexity stemming from feature interactions. On synthetic micro-array data, depth outperforms existing methods in robustness to irrelevant features and identifying complexity from feature interactions. Applied to case-control genotype and gene-expression micro-array datasets, the results reveal that a single feature of gene-expression data can account for over 90% of the performance of multi-feature model, confirming the adequacy of the commonly used differentially expressed gene (DEG) feature selection method for the gene expression data. Our study also demonstrates that constructing predictive models for genotype data is harder than gene expression data. The results in this paper provide evidence for the use of interpretable machine learning algorithms on microarray data.

Published
2023

697. Evolutionary approaches to explainable machine learning

Author

Zhou, Ryan, Hu, Ting, Zhou, Ryan, and Hu, Ting

Abstract

Machine learning models are increasingly being used in critical sectors, but their black-box nature has raised concerns about accountability and trust. The field of explainable artificial intelligence (XAI) or explainable machine learning (XML) has emerged in response to the need for human understanding of these models. Evolutionary computing, as a family of powerful optimization and learning tools, has significant potential to contribute to XAI/XML. In this chapter, we provide a brief introduction to XAI/XML and review various techniques in current use for explaining machine learning models. We then focus on how evolutionary computing can be used in XAI/XML, and review some approaches which incorporate EC techniques. We also discuss some open challenges in XAI/XML and opportunities for future research in this field using EC. Our aim is to demonstrate that evolutionary computing is well-suited for addressing current problems in explainability, and to encourage further exploration of these methods to contribute to the development of more transparent, trustworthy and accountable machine learning models.

Published
2023
Full Text
View/download PDF

698. Inhibitory effect of polysaccharide of Sargassum weizhouense on PCV2 induced inflammation in mice by suppressing histone acetylation

Author

Chen Hai-lan, Tan Hong-lian, Yang Jian, Song Manling, Feng Heyu, Kuang Na, Hu Wenyue, Chen Si-yu, Wei Ying-yi, and Hu Ting-jun

Subjects
Polysaccharide, Sargassum weizhouense, Inflammation, Histone acetylation, Porcine circovirus type 2, Therapeutics. Pharmacology, RM1-950
Abstract

Seaweeds are excellent source of bioactive compounds and seaweed-derived polysaccharides have demonstrated an array of biological effects. Here, we investigated the effect of polysaccharide of Sargassum weizhouense (PSW) on the inflammatory response in porcine circovirus type 2 (PCV2) infected mice and the underlying mechanism was studied according to the histone acetylation. After PCV2 infection, the levels of TNF-α, IL-1β, IL-6, IL-8, IL-10, MCP-1, COX-1, COX-2 and HAT in both serum and spleen were significantly increased (P

Published
2019
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results