CALL Related Papers
Title |
Author(s) |
Published in |
Download |
Comments |
| Automatic Text-Independent Pronunciation Scoring of Foreign Language Student Speech | L. Neumeyer H. Franco M. Weintraub P. Price |
ICSLP 1996 | [PDF] | 共提出了四種basic scoring方法: HMM log-likelihood score, segment classification score, segment duration scores, 和 timing scores |
| Automatic Pronunciation Scoring for Language Instruction | H. Franco L. Neumeyer Y. Kim O. Ronen |
ICASSP 1997 | [PDF] | 提出了HMM-based log-posterior probability score, 效果比之前的segment duration score和log-likelihood score好, 整句評分是由每個phone的評分再平均得來, 並提出了使用linear regression/nonlinear regression (neural network)/model estimation的方法來做score combination |
| Automatic Detection of Mispronunciation for Language Instruction | O. Ronen L. Neumeyer H. Franco |
Eurospeech 1997 | [PDF] | 使用mispronunciation network |
| A CALL System Using Speech Recognition to Train the Pronunciation of Japanese Long Vowels, the Mora Nasal and Mora Obstruents | G. Kawai K. Hirose |
Eurospeech 1997 | [PDF] | 自動辨識/回饋日文學習者在以下三種易混淆的音種: long/short vowel, mora/non-mora nasal, and mora/non-mora obstruent, 辨識只用duration長短來看, 會先用native corpus算出每個音的duration分佈 |
| Automatic Pronunciation Scoring of Specific Phone Segments for Language Instruction | Y. Kim H. Franco L. Neumeyer |
Eurospeech 1997 | [PDF] [PPT] |
提出了三種評分的方法, 利用 likelihood, posterior probility, 和 duration 來做評分 |
| Using Likelihood Ratios to PerformUtterance Verification in Automatic Pronunciation Assessment | F. de Wet C. Cucchiarini H. Strik L. Boves |
Eurospeech 1999 | [PDF] | |
| Automatic Scoring of Pronunciation Quality | L. Neumeyer H. Franco V. Digalakis M. Weintraub |
Speech Communication, 30:83–93, 2000. | [PDF] | 承接 eurospeech97 Kim et al 那篇, 有五種評分方法, 但看起來大同小異 |
| Combination of Machine Scores for Automatic Grading of Pronunciation Quality | H. Franco L. Neumeyer V. Digalakis O. Ronen |
Speech Communication 2000 | [PDF] | 提出了多種評分結合的方法, 包括 linear regression, neural network, distribution esitmation, 和 regression tree, 最後是 neural network 表現最好, 但調整參數也最為麻煩 |
| Phone-Level Pronunciation Scoring and Assessment for Interactive Language Learning | S. Witt S. Young |
Speech Communication, 30((2/3)):95-108, 2000 | [PDF] [PPT] |
這篇提出了 GoP 的方法來做 mispronunciation detection, 對 evaluation 的方法也有很詳細的論述 |
| English Speech Database Read by Japanese Learners for CALL System Development | N. Minematsu Y. Tomiyama K. Yoshimoto K. Shimizu S. Nakagawa M. Dantsuji S. Makino |
International Conference on Language Resources and Evaluation 2002 | [PDF] | ERJ corpus 介紹 #1 |
| Development of English Speech Database Read by Japanese to Support CALL Research | N. Minematsu Y. Tomiyama K. Yoshimoto K. Shimizu S. Nakagawa M. Dantsuji S. Makino |
International Conference on Acoustics 2004 | [PDF] | ERJ corpus 介紹 #2 (使用此 corpus 要 cite 這篇) |
| Automatic Pronunciation Assessment for Mandarin Chinese | J. C. Chen J. S. R. Jang J. Y. Li M. C. Wu |
ICME 2004 | [PDF] | |
| Segmental errors in Dutch as a second language how to establish priorities for CAPT | A. Neri C. Cucchiarini H. Srik |
InSTIL/ICALL 2004 | [PDF] | |
| Computer Assisted Spoken English Learning for Chinese in Taiwan | J. C. Chen J. L. Lo J. S. R. Jang |
ISCSLP 2004 | [PDF] | |
| Pronunciation Assessment Based upon the Phonological Distortions Observed in Language Learners Utterances | N. Minematsu | ICSLP 2004 | [PDF] | |
| The Multi-Channel Wall Street Journal Audio Visual Corpus (MC-WSJ-AV): Specification and Initial Experiment | M. Lincoln I. McCowan J. Vepa H. K. Maganti |
Automatic Speech Recognition and Understanding, 2005 IEEE Workshop, pages 357-362, 2005 | [PDF] | |
| ASR-Based Corrective Feedback on Pronunciation Does It Really Work | A. Neri C. Cucchiarini H. Strik |
ICSLP 2006 | [PDF] | |
| Non-Native Speech Databases | M. Raab R. Gruhn E. Noeth |
Proc. ASRU 2007 | [PDF] | Non-Native Speech Databases的詳細整理, 但很多連結都已年久失修了... |
| Mandarin Vowel Pronunciation Quality Evaluation by a Novel Formant Classification Method and its Combination with Traditional Algorithms | F. Pan Q. Zhao Y. Yan |
ICASSP 2008 | [PDF] | |
| The Goodness of Pronunciation Algorithm a Detailed Performance Study | S. Kanters C. Cucchiarini H. Strik |
SLaTE 2009 | [PDF] | (Best Paper Award) |
| Implementation of an Extended Recognition Network for Mispronunciation Detection and Diagnosis in Computer-Assisted Pronunciation Training | A. M. Harrison W. Lo X. Qian H. Meng |
SLaTE 2009 | [PDF] | |
| Computer Assisted Language Learning system based on dynamic question generation and error prediction for automatic speech recognition | H. Wang C. J. Waple T. Kawahara |
Speech Communication 2009 | [PDF] | |
| Automatic Pronunciation Scoring of Words and Sentences Independent from the Non-Natives First Language | T. Cincarek R. Gruhn C. Hacker E. Noth S. Nakamura |
Computer Speech and Language 2009 | [PDF] | 用了多種評分方法及評分結合方法 |
| Spoken English Assessment System for Non-Native Speakers Using Acoustic and Prosodic Features | Q. Shi K. Li S. L. Zhang S. M. Chu J. Xiao Z. J. Ou |
INTERSPEECH 2010 | [PDF] |
|
| Integration of Multilayer Regression Analysis with Structure-based Pronunciation Assessment | M. Suzuki Y. Qiao N. Minematsu K. Hirose |
Interspeech 2010 | [PDF] | |
| Automatic Evaluation of English Pronunciation by Japanese Speakers Using Various Acoustic Features and Pattern Recognition Techniques | K. Hirabayashi S. Nakagawa |
Interspeech 2010 | [PDF] | correlation 超高的一篇 paper, 用了15種 scoring 的方式 (有些很怪...), 最高 correlation 超過 0.9, nonnative corpus 包括 TED (Translanguage English Database) 和 ERJ (English Read by Japanese) |
| Landmark-based Automated Pronunciation Error Detection | S. Y. Yoon M. Hasegawa-Johnson R. Sproat |
Interspeech 2010 | [PDF] | 很囧的一篇paper, 用 GoP 和 SVM 算出 score 再用 SVM 做 score combination, 方法爛掉, 奇怪的做法也很多, 而且在四個步驟居然用了四個不同的 corpora |
| Discriminative Acoustic Model for Improving Mispronunciation Detection and Diagnosis in Computer-Aided Pronunciation Training (CAPT) | X. Qian F. Soong H. Meng |
Interspeech 2010 | [PDF] | |
| A New Approach for Automatic Tone Error Detection in Strong Accented Mandarin Based on Dominant Set | T. Zhu D. Ke Z. Chen B. Xu |
Interspeech 2010 | [PDF] | |
| Automatic Derivation of Phonological Rules for Mispronunciation Detection in a Computer-Assisted Pronunciation Training System | W. K. Lo S. Zhang H. Meng |
Interspeech 2010 | [PDF] | |
| Adapting a Duration Synthesis Model to Rate Childrens Oral Reading Prosody | M. Duong J. Mostow |
Interspeech 2010 | [PDF] | |
| Predicting Word Accuracy for the Automatic Speech Recognition of Non-Native Speech | S. Y. Yoon L. Chen K. Zechner |
Interspeech 2010 | [PDF] | |
| Regularized-MLLR Speaker Adaptation for Computer-Assisted Language Learning System | D. Luo Y. Qiao N. Minematsu Y. Yamauchi K. Hirose |
Interspeech 2010 | [PDF] | |
| Using Non-Native Error Patterns to Improve Pronunciation Verification | J. van Doremalen C. Cucchiarini H. Strik |
Interspeech 2010 | [PDF] | |
| Decision Tree Based Tone Modeling with Corrective Feedbacks for Automatic Mandarin Tone Assessment | H. C. Liao J. C. Chen S. C. Chang Y. H. Guan C. H. Lee |
Interspeech 2010 | [PDF] | |
| CASTLE a Computer-Assisted Stress Teaching and Learning Environment for Learners of English as a Second Language | J. Lu R. Wang L. C De Silva Y. Gao J. Liu |
Interspeech 2010 | [PDF] | |
| Exploring goodness of prosody by diverse matching templates | S. Huang H. Li S. Wang J. Liang B. Xu |
Interspeech 2010 | [PDF] | |
| Automatic reference independent evaluation of prosody quality using multiple knowledge fusions | S. Huang H. Li S. Wang J. Liang B. Xu |
Interspeech 2010 | [PDF] | |
| Developing A Chinese L2 Speech Database of Japanese Learners With Narrow-Phonetic Labels For Computer Assisted Pronunciation Training | W. Cao D. Wang J. Zhang Z. Xiong |
Interspeech 2010 | [PDF] | |
| Influence of musical training on perception of L2 speech | M. Sadakata L. van der Zanden K. Sekiyama |
Interspeech 2010 | [PDF] | |
| Learning words and speech units through natural interactions | J. Hornstein J. Santos-Victor |
Interspeech 2010 | [PDF] | |
| Quantitative, Notional, and Comprehensive Evaluations of Spontaneous Engaged Speech | G. Molholt M. J. Cabrera V. K. Kumar P. Thompsen |
The Computer Assisted Language Instruction Consortium (CALICO) 2011 | [PDF] | 評估口說能力的paper, 還沒看過... |
| New feature parameters for pronunciation evaluation in English presentations at international conferences | H. Kibishi S. Nakagawa |
Interspeech 2011 | [PDF] | 這篇是他們在 2010 Interspeech 那篇的延續, 我還沒看過 |
| Automatically assessing the ABCs Verification of children's spoken letter-names and letter-sounds | M. P. Black A. Kazemzadeh J. Tepperman S. S. Narayanan |
TSLP 2011 | [PDF] | |
| FLORA Fluent oral reading assessment of children's speech | D. Bolanos R. A. Cole W. Ward E. Borts E. Svirsky |
TSLP 2011 | [PDF] | |
| Two methods for assessing oral reading prosody | M. Duong J. Mostow S. Sitaram |
TSLP 2011 | [PDF] |
Title |
Author(s) |
Published in |
Download |
Comments |
| Pranking with Ranking | K. Crammer Y. Singer |
Advances in Neural Information Processing Systems (NIPS) 2001 | [PDF] |
用 perceptron 來做 learning to rank, 屬於 pointwise 的方法, 經典 |
| Learning to Rank using Gradient Descent | C. Burges T. Shaked E. Renshaw A. Lazier M. Deeds N. Hamilton G. Hullender |
ICML 2005 | [PDF] |
RankNet, 用 pairwise 的概念配上 neural network 來做 learning to rank, 也是經典的 paper |
| Learning to Rank: From Pairwise Approach to Listwise Approach | Z. Cao T. Qin T. Y. Liu M. F. Tsai H. Li |
ICML 2007 | [PDF] [PPT] |
寫的很棒的一篇 listwise learning to rank 的 paper, 數學推導寫的相當清楚, 很強大的一篇 paper |
| Learning to Rank with Ties | K. Zhou G. R. Xue H. Zha Y. Yu |
SIGIR 2008 | [PDF] [PPT] |
在 pairwise 的方法裡, 再加上 tie data 的使用, 讓有限資料的使用更有效率, 也是很強大的一篇 paper |
| Ranking Projection | Z. S. Chen | 20100203 Lab Meeting | [PPT] | 致生學長出國前想到的 idea, 後來有比較完整的 journal |
Title |
Author(s) |
Published in |
Download |
Comments |
| Detection of Accents, Phrase Boundaries, and Sentence Modality in German with Prosodic Features | V. Strom | Eurospeech 1995 | [PDF] |
|
| Acoustic Correlates of Linguistic Stress and Accent in Dutch and American English | A. Sluijter V. van Heuven |
ICSLP 1996 | [PDF] |
|
| Prosodic Prominence Detection in Speech | F. Tamburini | International Symposium on Signal Processing and its Applications, 2003 | [PDF]
[Summary] |
這篇 paper 說明了做 prominence detection, 用整個 syllable 和只用 syllable nucleus 效果並不會差太多, 另外他也用 pitch accent + stress 來做 prominence detection |
| Detecting Stress in Spoken English using Decision Trees and Support Vector Machines | H. Xie P. Andreae M. Zhang P. Warren |
Australasian Information Security, Data Mining and Web Intelligence, and Software Internalisation, 2004 | [PDF] |
|
| Practical Use of English Pronunciation System for Japanese Students in the CALL Classroom | Y. Tsubota T. Kawahara M. Dantsuji |
INTERSPEECH 2004 | [PDF] |
|
| Speech Rate Estimation via Temporal Correlation and Selected Sub-Band Correlation | S. Narayanan D. Wang |
ICASSP 2005 | [PDF] |
|
| Automatic Syllable Stress Detection using Prosodic Features for Pronunciation Evaluation of Language Learners | J. Tepperman S. Narayanan |
ICASSP 2005 | [PDF] |
清楚說明prominence/pitch accent/stress之間的差異, 並說明為何pitch相關特徵對stress detection仍是有用的特徵 |
| Loudness Predicts Prominence Fundamental Frequency Lends Little | G. Kochanski E. Grabe J. Coleman B. Rosner |
Journal of Acoustic Society of America, 2005 | [PDF] |
|
| An Automatic System for Detecting Prosodic Prominence in American English Continuous Speech | F. Tamburini C. Caini |
International Journal of Speech Technology, 2005 | [PDF] |
|
| An Acoustic Measure for Word Prominence in Spontaneous Speech | D. Wang S. Narayanan |
TASLP 2007 | [PDF] |
|
| Word stress assessment for computer aided language learning | J. P. Arias N. B. Yoma H. Vivanco |
Interspeech 2009 | [PDF] [Summary] | 這個方法比較兩句的音高和能量來決定兩句(字)的重音位置是否一樣, 需要老師音檔才能做評量 |
| Automatic Prediction of Childrens Reading Ability for High-level Literacy Assessment | M. P. Black J. Tepperman S. Narayanan |
TASLP 2011 | [PDF] |