Berlin Chen


2024

pdf bib
An Effective Automated Speaking Assessment Approach to Mitigating Data Scarcity and Imbalanced Distribution
Tien-Hong Lo | Fu-An Chao | Tzu-i Wu | Yao-Ting Sung | Berlin Chen
Findings of the Association for Computational Linguistics: NAACL 2024

Automated speaking assessment (ASA) typically involves automatic speech recognition (ASR) and hand-crafted feature extraction from the ASR transcript of a learner’s speech. Recently, self-supervised learning (SSL) has shown stellar performance compared to traditional methods. However, SSL-based ASA systems are faced with at least three data-related challenges: limited annotated data, uneven distribution of learner proficiency levels and non-uniform score intervals between different CEFR proficiency levels. To address these challenges, we explore the use of two novel modeling strategies: metric-based classification and loss re-weighting, leveraging distinct SSL-based embedding features. Extensive experimental results on the ICNALE benchmark dataset suggest that our approach can outperform existing strong baselines by a sizable margin, achieving a significant improvement of more than 10% in CEFR prediction accuracy.

pdf bib
DANCER: Entity Description Augmented Named Entity Corrector for Automatic Speech Recognition
Yi-Cheng Wang | Hsin-Wei Wang | Bi-Cheng Yan | Chi-Han Lin | Berlin Chen
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

End-to-end automatic speech recognition (E2E ASR) systems often suffer from mistranscription of domain-specific phrases, such as named entities, sometimes leading to catastrophic failures in downstream tasks. A family of fast and lightweight named entity correction (NEC) models for ASR have recently been proposed, which normally build on pho-netic-level edit distance algorithms and have shown impressive NEC performance. However, as the named entity (NE) list grows, the problems of phonetic confusion in the NE list are exacerbated; for example, homophone ambiguities increase substantially. In view of this, we proposed a novel Description Augmented Named entity CorrEctoR (dubbed DANCER), which leverages entity descriptions to provide additional information to facilitate mitigation of phonetic con-fusion for NEC on ASR transcription. To this end, an efficient entity description augmented masked language model (EDA-MLM) comprised of a dense retrieval model is introduced, enabling MLM to adapt swiftly to domain-specific entities for the NEC task. A series of experiments conducted on the AISHELL-1 and Homophone datasets confirm the effectiveness of our modeling approach. DANCER outperforms a strong baseline, the phonetic edit-distance-based NEC model (PED-NEC), by a character error rate (CER) reduction of about 7% relatively on AISHELL-1 for named entities. More notably, when tested on Homophone that contain named entities of high phonetic confusion, DANCER offers a more pronounced CER reduction of 46% relatively over PED-NEC for named entities. The code is available at https://github.com/Amiannn/Dancer.

pdf bib
An Effective Pronunciation Assessment Approach Leveraging Hierarchical Transformers and Pre-training Strategies
Bi-Cheng Yan | Jiun-Ting Li | Yi-Cheng Wang | Hsin Wei Wang | Tien-Hong Lo | Yung-Chang Hsu | Wei-Cheng Chao | Berlin Chen
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Automatic pronunciation assessment (APA) manages to quantify a second language (L2) learner’s pronunciation proficiency in a target language by providing fine-grained feedback with multiple pronunciation aspect scores at various linguistic levels. Most existing efforts on APA typically parallelize the modeling process, namely predicting multiple aspect scores across various linguistic levels simultaneously. This inevitably makes both the hierarchy of linguistic units and the relatedness among the pronunciation aspects sidelined. Recognizing such a limitation, we in this paper first introduce HierTFR, a hierarchal APA method that jointly models the intrinsic structures of an utterance while considering the relatedness among the pronunciation aspects. We also propose a correlation-aware regularizer to strengthen the connection between the estimated scores and the human annotations. Furthermore, novel pre-training strategies tailored for different linguistic levels are put forward so as to facilitate better model initialization. An extensive set of empirical experiments conducted on the speechocean762 benchmark dataset suggest the feasibility and effectiveness of our approach in relation to several competitive baselines.

2023

pdf bib
Auxiliary loss to attention head for end to end speaker diarization
Yi-Ting Yang | Jiun-Ting Li | Berlin Chen
Proceedings of the 35th Conference on Computational Linguistics and Speech Processing (ROCLING 2023)

pdf bib
Leveraging Dialogue Discourse Parsing in a Two-Stage Framework for Meeting Summarization
Yi-Ping Huang | Tien-Hong Lo | Berlin Chen
Proceedings of the 35th Conference on Computational Linguistics and Speech Processing (ROCLING 2023)

pdf bib
AaWLoss: An Artifact-aware Weighted Loss Function for Speech Enhancement
En-Lun Yu | Kuan-Hsun Ho | Berlin Chen
Proceedings of the 35th Conference on Computational Linguistics and Speech Processing (ROCLING 2023)

pdf bib
Enhancing Automated English Speaking Assessment for L2 Speakers with BERT and Wav2vec2.0 Fusion
Wen-Hsuan Peng | Hsin-Wei Wang | Sally Chen | Berlin Chen
Proceedings of the 35th Conference on Computational Linguistics and Speech Processing (ROCLING 2023)

pdf bib
Addressing the issue of Data Imbalance in Multi-granularity Pronunciation Assessment
Meng-Shin Lin | Hsin-Wei Wang | Tien-Hong Lo | Berlin Chen | Wei-Cheng Chao
Proceedings of the 35th Conference on Computational Linguistics and Speech Processing (ROCLING 2023)

pdf bib
KNOT-MCTS: An Effective Approach to Addressing Hallucinations in Generative Language Modeling for Question Answering
Chung-Wen Wu | Guan-Tang Huang | Yue-Yang He | Berlin Chen
Proceedings of the 35th Conference on Computational Linguistics and Speech Processing (ROCLING 2023)

pdf bib
The NTNU Super Monster Team (SPMT) system for the Formosa Speech Recognition Challenge 2023 - Hakka ASR
Tzu-Ting Yang | Hsin-Wei Wang | Meng-Ting Tsai | Berlin Chen
Proceedings of the 35th Conference on Computational Linguistics and Speech Processing (ROCLING 2023)

2022

pdf bib
A Preliminary Study on Automated Speaking Assessment of English as a Second Language (ESL) Students
Tzu-I Wu | Tien-Hong Lo | Fu-An Chao | Yao-Ting Sung | Berlin Chen
Proceedings of the 34th Conference on Computational Linguistics and Speech Processing (ROCLING 2022)

Due to the surge in global demand for English as a second language (ESL), developments of automated methods for grading speaking proficiency have gained considerable attention. This paper aims to present a computerized regime of grading the spontaneous spoken language for ESL learners. Based on the speech corpus of ESL learners recently collected in Taiwan, we first extract multi-view features (e.g., pronunciation, fluency, and prosody features) from either automatic speech recognition (ASR) transcription or audio signals. These extracted features are, in turn, fed into a tree-based classifier to produce a new set of indicative features as the input of the automated assessment system, viz. the grader. Finally, we use different machine learning models to predict ESL learners’ respective speaking proficiency and map the result into the corresponding CEFR level. The experimental results and analysis conducted on the speech corpus of ESL learners in Taiwan show that our approach holds great potential for use in automated speaking assessment, meanwhile offering more reliable predictive results than the human experts.

pdf bib
Building an Enhanced Autoregressive Document Retriever Leveraging Supervised Contrastive Learning
Yi-Cheng Wang | Tzu-Ting Yang | Hsin-Wei Wang | Yung-Chang Hsu | Berlin Chen
Proceedings of the 34th Conference on Computational Linguistics and Speech Processing (ROCLING 2022)

The goal of an information retrieval system is to retrieve documents that are most relevant to a given user query from a huge collection of documents, which usually requires time-consuming multiple comparisons between the query and candidate documents so as to find the most relevant ones. Recently, a novel retrieval modeling approach, dubbed Differentiable Search Index (DSI), has been proposed. DSI dramatically simplifies the whole retrieval process by encoding all information about the document collection into the parameter space of a single Transformer model, on top of which DSI can in turn generate the relevant document identities (IDs) in an autoregressive manner in response to a user query. Although DSI addresses the shortcomings of traditional retrieval systems, previous studies have pointed out that DSI might fail to retrieve relevant documents because DSI uses the document IDs as the pivotal mechanism to establish the relationship between queries and documents, whereas not every document in the document collection has its corresponding relevant and irrelevant queries for the training purpose. In view of this, we put forward to leveraging supervised contrastive learning to better render the relationship between queries and documents in the latent semantic space. Furthermore, an approximate nearest neighbor search strategy is employed at retrieval time to further assist the Transformer model in generating document IDs relevant to a posed query more efficiently. A series of experiments conducted on the Nature Question benchmark dataset confirm the effectiveness and practical feasibility of our approach in relation to some strong baseline systems.

pdf bib
International Journal of Computational Linguistics & Chinese Language Processing, Volume 27, Number 2, December 2022
Berlin Chen | Hung-Yu Kao
International Journal of Computational Linguistics & Chinese Language Processing, Volume 27, Number 2, December 2022

2021

pdf bib
A Study on Contextualized Language Modeling for Machine Reading Comprehension
Chin-Ying Wu | Yung-Chang Hsu | Berlin Chen
Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (ROCLING 2021)

With the recent breakthrough of deep learning technologies, research on machine reading comprehension (MRC) has attracted much attention and found its versatile applications in many use cases. MRC is an important natural language processing (NLP) task aiming to assess the ability of a machine to understand natural language expressions, which is typically operationalized by first asking questions based on a given text paragraph and then receiving machine-generated answers in accordance with the given context paragraph and questions. In this paper, we leverage two novel pretrained language models built on top of Bidirectional Encoder Representations from Transformers (BERT), namely BERT-wwm and MacBERT, to develop effective MRC methods. In addition, we also seek to investigate whether additional incorporation of the categorical information about a context paragraph can benefit MRC or not, which is achieved based on performing context paragraph clustering on the training dataset. On the other hand, an ensemble learning approach is proposed to harness the synergistic power of the aforementioned two BERT-based models so as to further promote MRC performance.

pdf bib
A Preliminary Study on Environmental Sound Classification Leveraging Large-Scale Pretrained Model and Semi-Supervised Learning
You-Sheng Tsao | Tien-Hong Lo | Jiun-Ting Li | Shi-Yan Weng | Berlin Chen
Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (ROCLING 2021)

With the widespread commercialization of smart devices, research on environmental sound classification has gained more and more attention in recent years. In this paper, we set out to make effective use of large-scale audio pretrained model and semi-supervised model training paradigm for environmental sound classification. To this end, an environmental sound classification method is first put forward, whose component model is built on top a large-scale audio pretrained model. Further, to simulate a low-resource sound classification setting where only limited supervised examples are made available, we instantiate the notion of transfer learning with a recently proposed training algorithm (namely, FixMatch) and a data augmentation method (namely, SpecAugment) to achieve the goal of semi-supervised model training. Experiments conducted on bench-mark dataset UrbanSound8K reveal that our classification method can lead to an accuracy improvement of 2.4% in relation to a current baseline method.

pdf bib
Exploring the Integration of E2E ASR and Pronunciation Modeling for English Mispronunciation Detection
Hsin-Wei Wang | Bi-Cheng Yan | Yung-Chang Hsu | Berlin Chen
Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (ROCLING 2021)

There has been increasing demand to develop effective computer-assisted language training (CAPT) systems, which can provide feedback on mispronunciations and facilitate second-language (L2) learners to improve their speaking proficiency through repeated practice. Due to the shortage of non-native speech for training the automatic speech recognition (ASR) module of a CAPT system, the corresponding mispronunciation detection performance is often affected by imperfect ASR. Recognizing this importance, we in this paper put forward a two-stage mispronunciation detection method. In the first stage, the speech uttered by an L2 learner is processed by an end-to-end ASR module to produce N-best phone sequence hypotheses. In the second stage, these hypotheses are fed into a pronunciation model which seeks to faithfully predict the phone sequence hypothesis that is most likely pronounced by the learner, so as to improve the performance of mispronunciation detection. Empirical experiments conducted a English benchmark dataset seem to confirm the utility of our method.

pdf bib
International Journal of Computational Linguistics & Chinese Language Processing, Volume 26, Number 1, June 2021
Chia-Hui Chang | Berlin Chen
International Journal of Computational Linguistics & Chinese Language Processing, Volume 26, Number 1, June 2021

pdf bib
The NTNU Taiwanese ASR System for Formosa Speech Recognition Challenge 2020
Fu-An Chao | Tien-Hong Lo | Shi-Yan Weng | Shih-Hsuan Chiu | Yao-Ting Sung | Berlin Chen
International Journal of Computational Linguistics & Chinese Language Processing, Volume 26, Number 1, June 2021

pdf bib
International Journal of Computational Linguistics & Chinese Language Processing, Volume 26, Number 2, December 2021
Berlin Chen | Hung-Yu Kao
International Journal of Computational Linguistics & Chinese Language Processing, Volume 26, Number 2, December 2021

2020

pdf bib
International Journal of Computational Linguistics & Chinese Language Processing, Volume 25, Number 1, June 2020
Chia-Hui Chang | Berlin Chen
International Journal of Computational Linguistics & Chinese Language Processing, Volume 25, Number 1, June 2020

pdf bib
基於端對端模型化技術之語音文件摘要 (Spoken Document Summarization Using End-to-End Modeling Techniques)
Tzu-En Liu | Shih-Hung Liu | Kuo-Wei Chang | Berlin Chen
International Journal of Computational Linguistics & Chinese Language Processing, Volume 25, Number 1, June 2020

pdf bib
Multi-view Attention-based Speech Enhancement Model for Noise-robust Automatic Speech Recognition
Fu-An Chao | Jeih-weih Hung | Berlin Chen
Proceedings of the 32nd Conference on Computational Linguistics and Speech Processing (ROCLING 2020)

pdf bib
Innovative Pretrained-based Reranking Language Models for N-best Speech Recognition Lists
Shih-Hsuan Chiu | Berlin Chen
Proceedings of the 32nd Conference on Computational Linguistics and Speech Processing (ROCLING 2020)

pdf bib
A Study on Contextualized Language Modeling for FAQ Retrieval
Wen-Ting Tseng | Yung-Chang Hsu | Berlin Chen
Proceedings of the 32nd Conference on Computational Linguistics and Speech Processing (ROCLING 2020)

pdf bib
Exploiting Text Prompts for the Development of an End-to-End Computer-Assisted Pronunciation Training System
Yu-Sen Cheng | Tien-Hong Lo | Berlin Chen
Proceedings of the 32nd Conference on Computational Linguistics and Speech Processing (ROCLING 2020)

pdf bib
Exploring Disparate Language Model Combination Strategies for Mandarin-English Code-Switching ASR
Wei-Ting Lin | Berlin Chen
Proceedings of the 32nd Conference on Computational Linguistics and Speech Processing (ROCLING 2020)

2019

pdf bib
使用生成對抗網路於強健式自動語音辨識的應用(Exploiting Generative Adversarial Network for Robustness Automatic Speech Recognition)
Ming-Jhang Yang | Fu-An Chao | Tien-Hong Lo | Berlin Chen
Proceedings of the 31st Conference on Computational Linguistics and Speech Processing (ROCLING 2019)

pdf bib
探究端對端語音辨識於發音檢測與診斷(Investigating on Computer-Assisted Pronunciation Training Leveraging End-to-End Speech Recognition Techniques)
Hsiu-Jui Chang | Tien-Hong Lo | Tzu-En Liu | Berlin Chen
Proceedings of the 31st Conference on Computational Linguistics and Speech Processing (ROCLING 2019)

pdf bib
基於階層式編碼架構之文本可讀性預測(A Hierarchical Encoding Framework for Text Readability Prediction)
Shi-Yan Weng | Hou-Chiang Tseng | Yao-Ting Sung | Berlin Chen
Proceedings of the 31st Conference on Computational Linguistics and Speech Processing (ROCLING 2019)

pdf bib
探究端對端混合模型架構於華語語音辨識 (An Investigation of Hybrid CTC-Attention Modeling in Mandarin Speech Recognition)
Hsiu-Jui Chang | Wei-Cheng Chao | Tien-Hong Lo | Berlin Chen
International Journal of Computational Linguistics & Chinese Language Processing, Volume 24, Number 1, June 2019

pdf bib
Can You Tell Me How to Get Past Sesame Street? Sentence-Level Pretraining Beyond Language Modeling
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
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Natural language understanding has recently seen a surge of progress with the use of sentence encoders like ELMo (Peters et al., 2018a) and BERT (Devlin et al., 2019) which are pretrained on variants of language modeling. We conduct the first large-scale systematic study of candidate pretraining tasks, comparing 19 different tasks both as alternatives and complements to language modeling. Our primary results support the use language modeling, especially when combined with pretraining on additional labeled-data tasks. However, our results are mixed across pretraining tasks and show some concerning trends: In ELMo’s pretrain-then-freeze paradigm, random baselines are worryingly strong and results vary strikingly across target tasks. In addition, fine-tuning BERT on an intermediate task often negatively impacts downstream transfer. In a more positive trend, we see modest gains from multitask training, suggesting the development of more sophisticated multitask and transfer learning techniques as an avenue for further research.

2018

pdf bib
結合鑑別式訓練與模型合併於半監督式語音辨識之研究 (Leveraging Discriminative Training and Model Combination for Semi-supervised Speech Recognition)
Tien-Hong Lo | Berlin Chen
International Journal of Computational Linguistics & Chinese Language Processing, Volume 23, Number 2, December 2018

pdf bib
會議語音辨識使用語者資訊之語言模型調適技術 (On the Use of Speaker-Aware Language Model Adaptation Techniques for Meeting Speech Recognition ) [In Chinese]
Ying-wen Chen | Tien-hong Lo | Hsiu-jui Chang | Wei-Cheng Chao | Berlin Chen
Proceedings of the 30th Conference on Computational Linguistics and Speech Processing (ROCLING 2018)

pdf bib
探討聲學模型的合併技術與半監督鑑別式訓練於會議語音辨識之研究 (Investigating acoustic model combination and semi-supervised discriminative training for meeting speech recognition) [In Chinese]
Tien-Hong Lo | Berlin Chen
Proceedings of the 30th Conference on Computational Linguistics and Speech Processing (ROCLING 2018)

pdf bib
探討鑑別式訓練聲學模型之類神經網路架構及優化方法的改進 (Discriminative Training of Acoustic Models Leveraging Improved Neural Network Architecture and Optimization Method) [In Chinese]
Wei-Cheng Chao | Hsiu-Jui Chang | Tien-Hong Lo | Berlin Chen
Proceedings of the 30th Conference on Computational Linguistics and Speech Processing (ROCLING 2018)

pdf bib
探索結合快速文本及卷積神經網路於可讀性模型之建立 (Exploring Combination of FastText and Convolutional Neural Networks for Building Readability Models) [In Chinese]
Hou-Chiang Tseng | Berlin Chen | Yao-Ting Sung
Proceedings of the 30th Conference on Computational Linguistics and Speech Processing (ROCLING 2018)

2017

pdf bib
探究不同領域文件之可讀性分析 (Exploring Readability Analysis on Multi-Domain Texts) [In Chinese]
Hou-Chiang Tseng | Yao-Ting Sung | Berlin Chen
Proceedings of the 29th Conference on Computational Linguistics and Speech Processing (ROCLING 2017)

pdf bib
使用查詢意向探索與類神經網路於語音文件檢索之研究 (Exploring Query Intent and Neural Network modeling Techniques for Spoken Document Retrieval) [In Chinese]
Tien-Hong Lo | Ying-Wen Chen | Berlin Chen | Kuan-Yu Chen | Hsin-Min Wang
Proceedings of the 29th Conference on Computational Linguistics and Speech Processing (ROCLING 2017)

pdf bib
序列標記與配對方法用於語音辨識錯誤偵測及修正 (On the Use of Sequence Labeling and Matching Methods for ASR Error Detection and Correction) [In Chinese]
Chia-Hua Wu | Chun-I Tsai | Hsiao-Tsung Hung | Yu-Chen Kao | Berlin Chen
Proceedings of the 29th Conference on Computational Linguistics and Speech Processing (ROCLING 2017)

pdf bib
當代非監督式方法之比較於節錄式語音摘要 (An Empirical Comparison of Contemporary Unsupervised Approaches for Extractive Speech Summarization) [In Chinese]
Shih-Hung Liu | Kuan-Yu Chen | Kai-Wun Shih | Berlin Chen | Hsin-Min Wang | Wen-Lian Hsu
International Journal of Computational Linguistics & Chinese Language Processing, Volume 22, Number 1, June 2017

pdf bib
語音文件檢索使用類神經網路技術 (On the Use of Neural Network Modeling Techniques for Spoken Document Retrieval) [In Chinese]
Tien-Hong Lo | Ying-Wen Chen | Kuan-Yu Chen | Hsin-Min Wang | Berlin Chen
International Journal of Computational Linguistics & Chinese Language Processing, Volume 22, Number 2, December 2017-Special Issue on Selected Papers from ROCLING XXIX

pdf bib
探究使用基於類神經網路之特徵於文本可讀性分類 (Exploring the Use of Neural Network based Features for Text Readability Classification) [In Chinese]
Hou-Chiang Tseng | Berlin Chen | Yao-Ting Sung
International Journal of Computational Linguistics & Chinese Language Processing, Volume 22, Number 2, December 2017-Special Issue on Selected Papers from ROCLING XXIX

2016

pdf bib
評估尺度相關最佳化方法於華語錯誤發音檢測之研究(Evaluation Metric-related Optimization Methods for Mandarin Mispronunciation Detection) [In Chinese]
Yao-Chi Hsu | Ming-Han Yang | Hsiao-Tsung Hung | Yi-Ju Lin | Berlin Chen
Proceedings of the 28th Conference on Computational Linguistics and Speech Processing (ROCLING 2016)

pdf bib
融合多任務學習類神經網路聲學模型訓練於會議語音辨識之研究(Leveraging Multi-task Learning with Neural Network Based Acoustic Modeling for Improved Meeting Speech Recognition) [In Chinese]
Ming-Han Yang | Yao-Chi Hsu | Hsiao-Tsung Hung | Ying-Wen Chen | Berlin Chen | Kuan-Yu Chen
Proceedings of the 28th Conference on Computational Linguistics and Speech Processing (ROCLING 2016)

pdf bib
使用字典學習法於強健性語音辨識(The Use of Dictionary Learning Approach for Robustness Speech Recognition) [In Chinese]
Bi-Cheng Yan | Chin-Hong Shih | Shih-Hung Liu | Berlin Chen
Proceedings of the 28th Conference on Computational Linguistics and Speech Processing (ROCLING 2016)

pdf bib
運用序列到序列生成架構於重寫式自動摘要(Exploiting Sequence-to-Sequence Generation Framework for Automatic Abstractive Summarization)[In Chinese]
Yu-Lun Hsieh | Shih-Hung Liu | Kuan-Yu Chen | Hsin-Min Wang | Wen-Lian Hsu | Berlin Chen
Proceedings of the 28th Conference on Computational Linguistics and Speech Processing (ROCLING 2016)

pdf bib
基於深層類神經網路及表示學習技術之文件可讀性分類(Classification of Text Readability Based on Deep Neural Network and Representation Learning Techniques)[In Chinese]
Hou-Chiang Tseng | Hsiao-Tsung Hung | Yao-Ting Sung | Berlin Chen
Proceedings of the 28th Conference on Computational Linguistics and Speech Processing (ROCLING 2016)

pdf bib
使用字典學習法於強健性語音辨識 (The Use of Dictionary Learning Approach for Robustness Speech Recognition) [In Chinese]
Bi-Cheng Yan | Chin-Hong Shih | Shih-Hung Liu | Berlin Chen
International Journal of Computational Linguistics & Chinese Language Processing, Volume 21, Number 2, December 2016

pdf bib
評估尺度相關最佳化方法於華語錯誤發音檢測之研究 (Evaluation Metric-related Optimization Methods for Mandarin Mispronunciation Detection) [In Chinese]
Yao-Chi Hsu | Ming-Han Yang | Hsiao-Tsung Hung | Yi-Ju Lin | Kuan-Yu Chen | Berlin Chen
International Journal of Computational Linguistics & Chinese Language Processing, Volume 21, Number 2, December 2016

pdf bib
融合多任務學習類神經網路聲學模型訓練於會議語音辨識之研究 (Leveraging Multi-Task Learning with Neural Network Based Acoustic Modeling for Improved Meeting Speech Recognition) [In Chinese]
Ming-Han Yang | Yao-Chi Hsu | Hsiao-Tsung Hung | Ying-Wen Chen | Kuan-Yu Chen | Berlin Chen
International Journal of Computational Linguistics & Chinese Language Processing, Volume 21, Number 2, December 2016

pdf bib
Learning to Distill: The Essence Vector Modeling Framework
Kuan-Yu Chen | Shih-Hung Liu | Berlin Chen | Hsin-Min Wang
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

In the context of natural language processing, representation learning has emerged as a newly active research subject because of its excellent performance in many applications. Learning representations of words is a pioneering study in this school of research. However, paragraph (or sentence and document) embedding learning is more suitable/reasonable for some tasks, such as sentiment classification and document summarization. Nevertheless, as far as we are aware, there is only a dearth of research focusing on launching unsupervised paragraph embedding methods. Classic paragraph embedding methods infer the representation of a given paragraph by considering all of the words occurring in the paragraph. Consequently, those stop or function words that occur frequently may mislead the embedding learning process to produce a misty paragraph representation. Motivated by these observations, our major contributions are twofold. First, we propose a novel unsupervised paragraph embedding method, named the essence vector (EV) model, which aims at not only distilling the most representative information from a paragraph but also excluding the general background information to produce a more informative low-dimensional vector representation for the paragraph. We evaluate the proposed EV model on benchmark sentiment classification and multi-document summarization tasks. The experimental results demonstrate the effectiveness and applicability of the proposed embedding method. Second, in view of the increasing importance of spoken content processing, an extension of the EV model, named the denoising essence vector (D-EV) model, is proposed. The D-EV model not only inherits the advantages of the EV model but also can infer a more robust representation for a given spoken paragraph against imperfect speech recognition. The utility of the D-EV model is evaluated on a spoken document summarization task, confirming the effectiveness of the proposed embedding method in relation to several well-practiced and state-of-the-art summarization methods.

2015

pdf bib
表示法學習技術於節錄式語音文件摘要之研究(A Study on Representation Learning Techniques for Extractive Spoken Document Summarization) [In Chinese]
Kai-Wun Shih | Berlin Chen | Kuan-Yu Chen | Shih-Hung Liu | Hsin-Min Wang
Proceedings of the 27th Conference on Computational Linguistics and Speech Processing (ROCLING 2015)

pdf bib
使用詞向量表示與概念資訊於中文大詞彙連續語音辨識之語言模型調適(Exploring Word Embedding and Concept Information for Language Model Adaptation in Mandarin Large Vocabulary Continuous Speech Recognition) [In Chinese]
Ssu-Cheng Chen | Kuan-Yu Chen | Hsiao-Tsung Hung | Berlin Chen
Proceedings of the 27th Conference on Computational Linguistics and Speech Processing (ROCLING 2015)

pdf bib
可讀性預測於中小學國語文教科書及優良課外讀物之研究(A Study of Readability Prediction on Elementary and Secondary Chinese Textbooks and Excellent Extracurricular Reading Materials) [In Chinese]
Yi-Nian Liu | Kuan-Yu Chen | Hou-Chiang Tseng | Berlin Chen
Proceedings of the 27th Conference on Computational Linguistics and Speech Processing (ROCLING 2015)

pdf bib
調變頻譜分解之改良於強健性語音辨識(Several Refinements of Modulation Spectrum Factorization for Robust Speech Recognition) [In Chinese]
Ting-Hao Chang | Hsiao-Tsung Hung | Kuan-Yu Chen | Hsin-Min Wang | Berlin Chen
Proceedings of the 27th Conference on Computational Linguistics and Speech Processing (ROCLING 2015)

pdf bib
融合多種深層類神經網路聲學模型與分類技術於華語錯誤發音檢測之研究(Exploring Combinations of Various Deep Neural Network based Acoustic Models and Classification Techniques for Mandarin Mispro-nunciation Detection)[In Chinese]
Yao-Chi Hsu | Ming-Han Yang | Hsiao-Tsung Hung | Yuwen Hsiung | Yao-Ting Hung | Berlin Chen
Proceedings of the 27th Conference on Computational Linguistics and Speech Processing (ROCLING 2015)

pdf bib
節錄式語音文件摘要使用表示法學習技術 (Extractive Spoken Document Summarization with Representation Learning Techniques) [In Chinese]
Kai-Wun Shih | Kuan-Yu Chen | Shih-Hung Liu | Hsin-Min Wang | Berlin Chen
International Journal of Computational Linguistics & Chinese Language Processing, Volume 20, Number 2, December 2015 - Special Issue on Selected Papers from ROCLING XXVII

pdf bib
調變頻譜分解技術於強健語音辨識之研究 (Investigating Modulation Spectrum Factorization Techniques for Robust Speech Recognition) [In Chinese]
Ting-Hao Chang | Hsiao-Tsung Hung | Kuan-Yu Chen | Hsin-Min Wang | Berlin Chen
International Journal of Computational Linguistics & Chinese Language Processing, Volume 20, Number 2, December 2015 - Special Issue on Selected Papers from ROCLING XXVII

2014

pdf bib
運用概念模型化技術於中文大詞彙連續語音辨識之語言模型調適 (Leveraging Concept Modeling Techniques for Language Model Adaptation in Mandarin Large Vocabulary Continuous Speech Recognition) [In Chinese]
Po-Han Hao | Su-Cheng Chen | Berlin Chen
Proceedings of the 26th Conference on Computational Linguistics and Speech Processing (ROCLING 2014)

pdf bib
探究新穎語句模型化技術於節錄式語音摘要 (Investigating Novel Sentence Modeling Techniques for Extractive Speech Summarization) [In Chinese]
Shih-Hung Liu | Kuan-Yu Chen | Yu-Lun Hsieh | Berlin Chen | Hsin-Min Wang | Wen-Lian Hsu
Proceedings of the 26th Conference on Computational Linguistics and Speech Processing (ROCLING 2014)

pdf bib
使用概念資訊於中文大詞彙連續語音辨識之研究 (Exploring Concept Information for Mandarin Large Vocabulary Continuous Speech Recognition) [In Chinese]
Po-Han Hao | Ssu-Cheng Chen | Berlin Chen
International Journal of Computational Linguistics & Chinese Language Processing, Volume 19, Number 4, December 2014 - Special Issue on Selected Papers from ROCLING XXVI

pdf bib
Leveraging Effective Query Modeling Techniques for Speech Recognition and Summarization
Kuan-Yu Chen | Shih-Hung Liu | Berlin Chen | Ea-Ee Jan | Hsin-Min Wang | Wen-Lian Hsu | Hsin-Hsi Chen
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

2013

pdf bib
改良語句模型技術於節錄式語音摘要之研究 (Improved Sentence Modeling Techniques for Extractive Speech Summarization) [In Chinese]
Shih-Hung Liu | Kuan-Yu Chen | Hsin-Min Wang | Wen-Lian Hsu | Berlin Chen
Proceedings of the 25th Conference on Computational Linguistics and Speech Processing (ROCLING 2013)

pdf bib
改良調變頻譜統計圖等化法於強健性語音辨識之研究 (Improved Modulation Spectrum Histogram Equalization for Robust Speech Recognition) [In Chinese]
Yu-Chen Kao | Berlin Chen
Proceedings of the 25th Conference on Computational Linguistics and Speech Processing (ROCLING 2013)

2012

pdf bib
改良式統計圖等化法強鍵性語音辨識之研究 (Improved Histogram Equalization Methods for Robust Speech Recognition) [In Chinese]
Hsin-Ju Hsieh | Jeih-weih Hung | Berlin Chen
Proceedings of the 24th Conference on Computational Linguistics and Speech Processing (ROCLING 2012)

pdf bib
遞迴式類神經網路語言模型應用額外資訊於語音辨識之研究 (Recurrent Neural Network-based Language Modeling with Extra Information Cues for Speech Recognition) [In Chinese]
Bang-Xuan Huang | Hank Hao | Menphis Chen | Berlin Chen
Proceedings of the 24th Conference on Computational Linguistics and Speech Processing (ROCLING 2012)

pdf bib
A Comparative Study of Methods for Topic Modeling in Spoken Document Retrieval
Shih-Hsiang Lin | Berlin Chen
International Journal of Computational Linguistics & Chinese Language Processing, Volume 17, Number 1, March 2012

pdf bib
語音辨識使用統計圖等化方法 (Speech Recognition Leveraging Histogram Equalization Methods) [In Chinese]
Hsin-Ju Hsieh | Jeih-weih Hung | Berlin Chen
International Journal of Computational Linguistics & Chinese Language Processing, Volume 17, Number 4, December 2012-Special Issue on Selected Papers from ROCLING XXIV

2011

pdf bib
An Effective and Robust Framework for Transliteration Exploration
Ea-Ee Jan | Niyu Ge | Shih-Hsiang Lin | Berlin Chen
Proceedings of 5th International Joint Conference on Natural Language Processing

pdf bib
實證探究多種鑑別式語言模型於語音辨識之研究 (Empirical Comparisons of Various Discriminative Language Models for Speech Recognition) [In Chinese]
Min-Hsuan Lai | Bang-Xuan Huang | Kuan-Yu Chen | Berlin Chen
Proceedings of the 23rd Conference on Computational Linguistics and Speech Processing (ROCLING 2011)

pdf bib
機率式調變頻譜分解於強健性語音辨識 (Probabilistic Modulation Spectrum Factorization for Robust Speech Recognition) [In Chinese]
Wen-Yi Chu | Yu-Chen Kao | Berlin Chen | Jeih-Weih Hung
ROCLING 2011 Poster Papers

2010

pdf bib
鑑別式語言模型於語音辨識結果重新排序之研究 (Exploiting Discriminative Language Models for Reranking Speech Recognition Hypotheses) [In Chinese]
Chia-Wen Liu | Shih-Hsiang Lin | Berlin Chen
Proceedings of the 22nd Conference on Computational Linguistics and Speech Processing (ROCLING 2010)

pdf bib
整合邊際資訊於鑑別式聲學模型訓練方法之比較研究 (A Comparative Study on Margin-Based Discriminative Training of Acoustic Models) [In Chinese]
Yueng-Tien Lo | Berlin Chen
Proceedings of the 22nd Conference on Computational Linguistics and Speech Processing (ROCLING 2010)

pdf bib
A Risk Minimization Framework for Extractive Speech Summarization
Shih-Hsiang Lin | Berlin Chen
Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics

2009

pdf bib
相似度比率式鑑別分析應用於大詞彙連續語音辨識 (Likelihood Ratio Based Discriminant Analysis for Large Vocabulary Continuous Speech Recognition) [In Chinese]
Hung-Shin Lee | Berlin Chen
Proceedings of the 21st Conference on Computational Linguistics and Speech Processing

pdf bib
主題語言模型於大詞彙連續語音辨識之研究 (On the Use of Topic Models for Large-Vocabulary Continuous Speech Recognition) [In Chinese]
Kuan-Yu Chen | Berlin Chen
Proceedings of the 21st Conference on Computational Linguistics and Speech Processing

2008

bib
Proceedings of the 20th Conference on Computational Linguistics and Speech Processing
Chao-Lin Liu | Berlin Chen
Proceedings of the 20th Conference on Computational Linguistics and Speech Processing

pdf bib
Improved Minimum Phone Error based Discriminative Training of Acoustic Models for Mandarin Large Vocabulary Continuous Speech Recognition
Shih-Hung Liu | Fang-Hui Chu | Yueng-Tien Lo | Berlin Chen
International Journal of Computational Linguistics & Chinese Language Processing, Volume 13, Number 3, September 2008: Special Issue on Selected Papers from ROCLING XIX

2007

bib
Proceedings of the 19th Conference on Computational Linguistics and Speech Processing
Kuang-Hua Chen | Berlin Chen
Proceedings of the 19th Conference on Computational Linguistics and Speech Processing

pdf bib
改善以最小化音素錯誤為基礎的鑑別式聲學模型訓練於中文連續語音辨識之研究 (Improved Minimum Phone Error based Discriminative Training of Acoustic Models for Chinese Continuous Speech Reconigtion) [In Chinese]
Shih-Hung Liu | Fang-Hui Chu | Berlin Chen
Proceedings of the 19th Conference on Computational Linguistics and Speech Processing

bib
ROCLING 2007 Poster Papers
Kuang-Hua Chen | Berlin Chen
ROCLING 2007 Poster Papers

pdf bib
A Comparative Study of Histogram Equalization (HEQ) for Robust Speech Recognition
Shih-Hsiang Lin | Yao-Ming Yeh | Berlin Chen
International Journal of Computational Linguistics & Chinese Language Processing, Volume 12, Number 2, June 2007

2006

pdf bib
統計圖等化法於雜訊語音辨識之進一步研究 (An Improved Histogram Equalization Approach for Robust Speech Recognition) [In Chinese]
Shih-Hsiang Lin | Yao-Ming Yeh | Berlin Chen
Proceedings of the 18th Conference on Computational Linguistics and Speech Processing

pdf bib
An Empirical Study of Word Error Minimization Approaches for Mandarin Large Vocabulary Continuous Speech Recognition
Jen-Wei Kuo | Shih-Hung Liu | Hsin-Min Wang | Berlin Chen
International Journal of Computational Linguistics & Chinese Language Processing, Volume 11, Number 3, September 2006: Special Issue on Selected Papers from ROCLING XVII

2005

pdf bib
風險最小化準則在中文大詞彙連續語音辨識之研究 (Risk Minimization Criterion for Mandarin Large Vocabulary Continuous Speech Recognition) [In Chinese]
Jen-Wei Kuo | Shih-Hung Liu | Berlin Chen
Proceedings of the 17th Conference on Computational Linguistics and Speech Processing

pdf bib
Lightly Supervised and Data-Driven Approaches to Mandarin Broadcast News Transcription
Berlin Chen | Jen-Wei Kuo | Wen-Hung Tsai
International Journal of Computational Linguistics & Chinese Language Processing, Volume 10, Number 1, March 2005

pdf bib
MATBN: A Mandarin Chinese Broadcast News Corpus
Hsin-Min Wang | Berlin Chen | Jen-Wei Kuo | Shih-Sian Cheng
International Journal of Computational Linguistics & Chinese Language Processing, Volume 10, Number 2, June 2005: Special Issue on Annotated Speech Corpora

2004

pdf bib
非監督式學習於中文電視新聞自動轉寫之初步應用 (Unsupervised Learning for Chinese Broadcast News Transcription) [In Chinese]
Jen-Wei Kuo | Wen-Hung Tsai | Berlin Chen
Proceedings of the 16th Conference on Computational Linguistics and Speech Processing

2001

pdf bib
Mandarin-English Information: Investigating Translingual Speech Retrieval
Helen Meng | Berlin Chen | Sanjeev Khudanpur | Gina-Anne Levow | Wai-Kit Lo | Douglas Oard | Patrick Shone | Karen Tang | Hsin-Min Wang | Jianqiang Wang
Proceedings of the First International Conference on Human Language Technology Research

Search