activity
20152024
most citedWhat do you learn from context? Probing for sentence structure in contextualized word representations

139 citations · 207 across the 14 of their papers we have counts for

collaborators
Showing 2021Show all

8 papers · 1 filter

cs.SD20215 cited

Improving End-To-End Modeling for Mispronunciation Detection with Effective Augmentation Mechanisms

Tien-Hong Lo, Yao-Ting Sung, Berlin Chen

Recently, end-to-end (E2E) models, which allow to take spectral vector sequences of L2 (second-language) learners' utterances as input and produce the corresponding phone-level seq…

eess.AS2021

Cross-domain Single-channel Speech Enhancement Model with Bi-projection Fusion Module for Noise-robust ASR

Fu-An Chao, Jeih-weih Hung, Berlin Chen

In recent decades, many studies have suggested that phase information is crucial for speech enhancement (SE), and time-domain single-channel speech enhancement techniques have show…

cs.MM20212 cited

Towards Robust Mispronunciation Detection and Diagnosis for L2 English Learners with Accent-Modulating Methods

Shao-Wei Fan Jiang, Bi-Cheng Yan, Tien-Hong Lo +2

With the acceleration of globalization, more and more people are willing or required to learn second languages (L2). One of the major remaining challenges facing current mispronunc…

eess.AS20213 cited

TENET: A Time-reversal Enhancement Network for Noise-robust ASR

Fu-An Chao, Shao-Wei Fan Jiang, Bi-Cheng Yan +2

Due to the unprecedented breakthroughs brought about by deep learning, speech enhancement (SE) techniques have been developed rapidly and play an important role prior to acoustic m…

cs.CL20215 cited

Cross-utterance Reranking Models with BERT and Graph Convolutional Networks for Conversational Speech Recognition

Shih-Hsuan Chiu, Tien-Hong Lo, Fu-An Chao +1

How to effectively incorporate cross-utterance information cues into a neural language model (LM) has emerged as one of the intriguing issues for automatic speech recognition (ASR)…

cs.CL202142 cited

Innovative Bert-based Reranking Language Models for Speech Recognition

Shih-Hsuan Chiu, Berlin Chen

More recently, Bidirectional Encoder Representations from Transformers (BERT) was proposed and has achieved impressive success on many natural language processing (NLP) tasks such…