Berlin Chen

Investigating Modulation Spectrum Factorization Techniques for Robust Speech Recognition

2015

The performance of an automatic speech recognition (ASR) system often deteriorates sharply due to the interference from varying environmental noise. As such, the development of effective and efficient robustness techniques has long been a challenging …

Effective FAQ Retrieval and Question Matching With Unsupervised Knowledge Injection

2020 · arXiv (Cornell University)

Frequently asked question (FAQ) retrieval, with the purpose of providing information on frequent questions or concerns, has far-reaching applications in many areas, where a collection of question-answer (Q-A) pairs compiled a priori can be employed …

An Effective Strategy for Modeling Score Ordinality and Non-uniform Intervals in Automated Speaking Assessment

2025 · arXiv (Cornell University)

A recent line of research on automated speaking assessment (ASA) has benefited from self-supervised learning (SSL) representations, which capture rich acoustic and linguistic patterns in non-native speech without underlying assumptions of feature curation. However, speech-based …

Can You Tell Me How to Get Past Sesame Street? Sentence-Level Pretraining Beyond Language Modeling

2019

Alex Wang, Jan Hula, Patrick Xia, Raghavendra Pappagari, R. Thomas McCoy, Roma Patel, Najoung Kim, Ian Tenney, Yinghui Huang, Katherin Yu, Shuning Jin, Berlin Chen, Benjamin Van Durme, Edouard Grave, Ellie Pavlick, Samuel R. Bowman. …

What do you learn from context? Probing for sentence structure in\n contextualized word representations

2019 · arXiv (Cornell University)

Contextualized representation models such as ELMo (Peters et al., 2018a) and\nBERT (Devlin et al., 2018) have recently achieved state-of-the-art results on a\ndiverse array of downstream NLP tasks. Building on recent token-level probing\nwork, we introduce a …