PaperMetrixاكتشاف قائم على الأدلة
AR
لغة الواجهة English EN العربية AR Türkçe TR
إنشاء حساب
ملف الباحث

Yiming Wang

6 أوراق في مجموعة PaperMetrix

المنشورات

أوراق هذا المؤلف

  1. CTCBERT: Advancing Hidden-unit BERT with CTC Objectives

    2022 · arXiv (Cornell University)

    In this work, we present a simple but effective method, CTCBERT, for advancing hidden-unit BERT (HuBERT). HuBERT applies a frame-level cross-entropy (CE) loss, which is similar to most acoustic model training. However, CTCBERT performs the …

  2. Oracle-guided Contrastive Clustering

    2022 · arXiv (Cornell University)

    Deep clustering aims to learn a clustering representation through deep architectures. Most of the existing methods usually conduct clustering with the unique goal of maximizing clustering performance, that ignores the personalized demand of clustering tasks.% …

  3. Using Deep Neural Network Approach for Multiple-Class Assessment of Digital Mammography

    2022 · Healthcare

    According to the Health Promotion Administration in the Ministry of Health and Welfare statistics in Taiwan, over ten thousand women have breast cancer every year. Mammography is widely used to detect breast cancer. However, it …

  4. Harnessing Large Language Models for Training-free Video Anomaly Detection

    2024 · arXiv (Cornell University)

    Video anomaly detection (VAD) aims to temporally locate abnormal events in a video. Existing works mostly rely on training deep models to learn the distribution of normality with either video-level supervision, one-class supervision, or in …

  5. Applying AI to English Speaking and Writing Instruction in Higher Education: A SWOT Analysis

    2025 · Springer Link (Chiba Institute of Technology)

    As artificial intelligence (AI) becomes more integrated into education, its role in supporting English language learning has drawn increasing attention. This paper explores how AI technologies impact the development of English speaking and writing skills, …

  6. A Pruned Rnnlm Lattice-Rescoring Algorithm for Automatic Speech Recognition

    2018

    Lattice-rescoring is a common approach to take advantage of recurrent neural language models in ASR, where a word-lattice is generated from 1st-pass decoding and the lattice is then rescored with a neural model, and ann-gram …