Maximum mutual information estimation of hidden Markov model parameters for speech recognition

An inequality and associated maximization technique in statistical estimation of probabilistic functions of a Markov process

Baum, L. E. (1972) · Medical Entomology and Zoology · Cited by 1,405

A Maximum Likelihood Approach to Continuous Speech Recognition

Bahl, L. R., Jelinek, F., & Mercer, R. L. (1983) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.1983.4767370 · Cited by 1,220

Some experiments with large-vocabulary isolated-word sentence recognition

Bahl, L. R., Das, S. K., de Souza, P., Jelinek, F., Katz, S., Mercer, R. L., & Picheny, M. (2005) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.1984.1172520 · Cited by 19

Discriminative training using the trusted expectation maximization

Hifny, Y., & Gao, Y. (2008) · Interspeech (USB) · doi:10.21437/interspeech.2008-115 · Cited by 1

A MMI Codebook Design for MVQHMM Speech Recognition

Peinado, A. M., Segura, J. C., Rubio-Ayuso, A. J., Sánchez, V., & Benı́tez, C. (1995) · Springer eBooks · doi:10.1007/978-3-642-57745-1_19 · Cited by 1

THE SIMILARITY MEASURE AMONG ACOUSTIC MODELS AND ITS TWO APPLICATIONS

Wu, J., Wu, W., & Fang, D. (1998)

Mutual Information Based Gesture Recognition

Harding, P., Topsom, M., & Costen, N. P. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-23672-3_69

Discriminant Acoustic Probability Estimation

Gold, B., Morgan, N. H., & Ellis, D. P. W. (2011) · doi:10.1002/9781118142882.ch27

Fundamentals of Automatic Speech Recognition

Junqua, J.-C., & Haton, J. (1996) · Kluwer international series in engineering and computer science · doi:10.1007/978-1-4613-1297-0_3 · Cited by 1

Fast Discriminative Training

Li, Q. (2011) · Signals and communication technology · doi:10.1007/978-3-642-23731-7_13

Improving speech recognition accuracy with contextual phonemes and MMI training

Derouault, A.-M., & Mérialdo, B. (2003) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.1989.266377

Apprentissage de mélanges de gaussiens par maximisation de la marge avec SMO

Tri, T. M., & Artières, T. (2007) · HAL

Approximated Mutual Information Training for Speech Recognition Using Myoelectric Signals

Guo, H. J., & Chan, A. D. C. (2006) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/iembs.2006.259992

Adaptation and Discriminative Training of Acoustic Models

Estève, Y., & Deléglise, P. (2012) · doi:10.1002/9781118392683.ch11

Hierarchical Command Recognition Based on Large Margin Hidden Markov Models

Dymarski, P. (2011) · InTech eBooks · doi:10.5772/14747

Optimizing Hidden Markov Models For Chinese An-Set Syllables

He, Q., & Kwong, S. (1998) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.36916

Approximations to the MMI criterion and their effect on lattice-based MMIPreprint

Wegmann, S. (2010) · arXiv (Cornell University) · doi:10.48550/arxiv.1002.0773

MMI-based-training for a probabilistic neural network

Bu, N., Tsuji, T., & Fukuda, O. (2004) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2003.1223987

Statistical analysis of geodetic networks for detecting regional events

Granat, R. A. (2004)

Hidden Markov Models

Vaseghi, S. V. (1996) · Vieweg+Teubner eBooks · doi:10.1007/978-3-322-92773-6_4

An equivalent-class based MMI learning method for MGCPM

Luo, C., Zheng, F., & Xu, M. (2000) · International Conference on Spoken Language Processing (ICSLP) · doi:10.21437/icslp.2000-771

A comparative study of RPCL and MCE based discriminative training methods for LVCSR

Pang, Z., Tu, S., Wu, X. H., & Xu, L. (2014) · Neurocomputing · doi:10.1016/j.neucom.2013.05.060

Discriminative Training for Native Chinese Speakers' Pronunciation Proficiency Evaluation

Yan, K. (2012) · Applied Mechanics and Materials · doi:10.4028/www.scientific.net/amm.195-196.521

Comparison of discrete and continuous classifier-based HMM.

Kawahara, T., & Doshita, S. (1992) · Journal of the Acoustical Society of Japan (E) · doi:10.1250/ast.13.361

I-smooth for improved minimum classification error training

Li, H., & Munteanu, C. (2010) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2010.5495109

Using a speaker-adaptable, task-customisable, dictation system for high accuracy text input: A case study

Sharman, R. A. (1997) · Speech Communication · doi:10.1016/s0167-6393(97)00058-7

Improvement Comparison of Different Lattice-based Discriminative Training Methods in Chinese-monolingual and Chinese-English-bilingual Speech Recognition

Qian, Y., Shan, Y., Wang, L., & Jia, L. I. U. (2012) · Acta Automatica Sinica · doi:10.1016/s1874-1029(11)60288-7

Vision-based technique for secure recognition of voice-less commands

Yau, W. C., Kumar, D., & Weghorn, H. (2008) · International Journal of Electronic Security and Digital Forensics · doi:10.1504/ijesdf.2008.021450

Optimization on decoding graphs using soft margin estimation

Abdelhamid, A. A., & Abdulla, W. H. (2013) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipa.2013.6694226

Multilevel sampling and aggregation for discriminative training

Zhao, Y., Zhao, T., & Chen, X. (2014) · International Symposium on Chinese Spoken Language Processing (ISCSLP) · doi:10.1109/iscslp.2014.6936677

Discriminative speaker adaptation with eigenvoices

Luo, J., Ou, Z., & Wang, Z. (2005) · Interspeech (USB) · doi:10.21437/interspeech.2005-168

Estimating acoustic-labial weights in connected speech recognition systems based on HMM

Jourlin, P. (2002) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/icsmc.1997.625743

Discriminative training via minimization of risk estimates based on Parzen smoothing

McDermott, E., & Katagiri, S. (2006) · Applied Intelligence · doi:10.1007/s10489-006-8865-0

Comparison of frame margin probability training to other discriminative methods for multi-condition speech recognition

Li, H., Li, X., & O’Shaughnessy, D. D. (2008) · International Conference on Audio, Language and Image Processing · doi:10.1109/icalip.2008.4590005

Model topology selection for isolated word recognition

Laface, P., & Fissore, L. (2002) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.1994.389215

Probabilistic Sequence Models with Speech and Language Applications

Henter, G. E. (2013) · KTH Publication Database DiVA (KTH Royal Institute of Technology)

Discovering relations among discriminative training objectives [speak recognition applications]

Li, Q. L. (2004) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2004.1325915

Optimizing acoustic models for commercial speech recognition using foreground scores and data weighting

Boies, D., Strope, B. P., Weintraub, M., & Wu, S.-L. (2004) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2004.1326111

Sistemas produtivos e inovativos locais como indutores do desenvolvimento sustentável

Fernandes, C. T. C. (2008) · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas)

A supervised two-channel learning method for hidden Markov model and application on lip reading

Foo, S. W., & Dong, L. (2002) · DR-NTU (Nanyang Technological University)

Context-dependent multi-class classification with unknown observation and class distributions with applications to bioinformatics

Baras, A. S., & Baras, J. S. (2009) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2009.5400269

Algorithm Optimizations: Low Memory Footprint

Vasilache, M. (2008) · Advances in pattern recognition · doi:10.1007/978-1-84800-143-5_11

Discriminative Training of Subspace Gaussian Mixture Model for Pattern Classification

Liu, X.-H., & Liu, C. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-14922-1_27

Discriminative Training for direct minimization of deletion, insertion and substitution errors

Shin, S.-H., Jung, H., & Juang, B.-H. F. (2011) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2011.5947561

DISCRIMINATIVE LEARNING FOR SPEECH RECOGNITION

Dehzangi, O. (2012)

A Discriminative Training Algorithm for

Ben-Yishai, A., & Burshtein, D. (2004)

( Modeling, criteria, optimization, implementation, and performance )

Heigold, G., Ney, H., Schlüter, R., & Wiesler, S. (2012)

Machine Learning for Ambient Intelligence: Boosting in Automatic Speech Recognition

Meyer, C., & Beyerlein, P. (2004) · Philips Research · doi:10.1007/978-94-017-0703-9_9

An Alternative Way to Discriminative Training

Psutka, J. (2014)

Türkçe Haber Bültenlerinin Açõk Kaynak Yazõlõmlar ile Yazõlandõrõlmasõ Turkish Broadcast News Transcription with Open-Source Software

gan, D. ̆. (2009)

THE MIDDLE EAST TECHNICAL UNIVERSITY

Arica, I. (2003)

Investigations on search methods for speech recognition using weighted finite state transducers

Rybach, D., & Ney, H. (2014) · RWTH Publications (RWTH Aachen)

Objectives for Discriminative Training

Li, Q. (2011) · Signals and communication technology · doi:10.1007/978-3-642-23731-7_12

音声ドキュメントの音声認識,整形,要約に関する研究

藤井, 康. (2012) · Institutional Repositories DataBase (IRDB)

Ensemble learning method for hidden markov models.

Hamdi, A. (2014) · doi:10.18297/etd/1706

Design of loss functions and feature transformation for minimum classification error based automatic speech recognition

Ratnagiri, M. (2011) · Rutgers University Community Repository (Rutgers University) · doi:10.7282/t3gt5mtt

Acoustic segment modeling and preference ranking for music information retrieval

Reed, J. T. (2010) · SMARTech Repository (Georgia Institute of Technology)

An Information Reinstatement Dealing with Machine Learning

Parwej, F., & Alquhayz, H. (2016) · Transactions on Machine Learning and Artificial Intelligence · doi:10.14738/tmlai.41.1691

Spontán magyar nyelv ű beszéd gépi felismerése nyelvspecifikus szabályok nélkül

Mihajlik, P. (2010)

Diseño de un sistema de comunicación entre personas sordas y personas oyentes

Martínez-Aponte, J. M., & Stivenson-Pinto, S. (2015) · ITECKNE Innovación e Investigación en Ingeniería · doi:10.15332/iteckne.v12i2.1240

présentée à l'Université d'Avignon et des Pays de Vaucluse pour obtenir le diplôme de DOCTORAT

Doctorale, É. (2013)

A genetic classication error methodfor speech recognition

Kwong, S. (2002)

Modèles de Markov cachés pour l'estimation de plusieurs fréquences fondamentales.

Jordan, M. I., & Bach, F. (2005)

聚集事後機率線性迴歸調適演算法應用於語音辨識 (Aggregate a Posteriori Linear Regression for Speech Recognition) [In Chinese]

Huang, C., Wang, Y.-K., & Chien, J. (2004) · International Conference on Computational Linguistics

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]

Liu, C.-W., Lin, S.-H., & Chen, B. (2010) · International Conference on Computational Linguistics

Anti-Models:

Vaněk, J., & Psutka, J. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10816-2_54

Compensation with prior knowledge

Li, J., Li, D., Haeb‐Umbach, R., & Gong, Y. (2015) · Elsevier eBooks · doi:10.1016/b978-0-12-802398-3.00005-2

Entrenamiento discriminativo de componentes principales ocultas de Markov aplicado a detección de estados funcionales en bioseñales

Cuestas, R., & Johana, B. (2009) · Americanae (AECID Library)

Object recognition using hybrid boosting methodPreprint

Ashfaq, O. (2016) · doi:10.7287/peerj.preprints.2220v1

Adaptive boosting for automatic speech recognition

Nguyen, K. (2015) · doi:10.17760/d20200410

Analysis and comparison of discriminative training objectives

Li, Q. (2004) · International Conference on Natural Language Processing and Knowledge Engineering (NLPKE) · doi:10.1109/nlpke.2003.1275964

Morpho-Syntactic Tagging of Text in “Baoule” Language Based on Hidden Markov Models (HMM)

Konan, H. K., Gooré, B. T., Gbégbé, R., & Asseu, O. (2016) · Journal of Software Engineering and Applications · doi:10.4236/jsea.2016.910034

Improved feature vectors using N-to-1 Gaussian MFCC transformation for automatic speech recognition system

Lachhab, O., & Haj, E. H. I. E. (2016) · doi:10.1109/icmcs.2016.7905523

Handwriting and Speech Recognition: From Bayes Decision Rule to Deep Neural Networks

Ney, H. (2016) · RWTH Publications (RWTH Aachen)

Response Generation For An Open-Ended Conversational Agent

Dziri, N. (2018) · ERA: Education and Research Archive (University of Alberta) · doi:10.7939/r3t43jj70

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]

Chao, W.-C., Chang, H.-J., Lo, T.-H., & Chen, B. (2018) · International Conference on Computational Linguistics

Using Convolution and Sequence-discriminative Training to Improving Children Speech Recognition

Meng, F., Peng, S., & Zhang, G. (2019) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc47483.2019.9023109

Large-Margin Structured Prediction Extensions of Neural Networks for Automatic Speech Recognition

Ravuri, S. V. (2015) · UC Berkeley

Context-Dependent Classification

Theodoridis, S., & Koutroumbas, K. (2006) · Elsevier eBooks · doi:10.1016/b978-012369531-4/50009-3

Complexity of the TDNN Acoustic Model with Respect to the HMM Topology

Psutka, J., Vaněk, J., & Pražák, A. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58323-1_50

Frame-level SpecAugment for Deep Convolutional Neural Networks in Hybrid ASR SystemsPreprint

Li, X., Zhang, Y., Zhuang, X., & Liu, D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.04094

DeepMI: A Mutual Information Based Framework For Unsupervised Deep Learning of TasksPreprint

Kumar, A., & Behera, L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.06411 · Cited by 1

Last Minute Medical Appointments No-Show Management

Sousa, D. M., & Vasconcelos, A. (2020) · International Journal of Healthcare Information Systems and Informatics · doi:10.4018/ijhisi.2020100102

Off-line Arabic Handwritten Recognition Using a Novel Hybrid HMM-DNN Model

BabaAli, B., & Rekabdar, B. (2021) · Signal and Data Processing · doi:10.29252/jsdp.17.4.155

Improving the Computational Efficiency of Training and Application of Neural Language Models for Automatic Speech Recognition

Xu, H. (2020)

Optimal generative and discriminative acoustic model training for speech recognition

Joshi, N. (2021) · doi:10.32920/ryerson.14664396.v1

An extension of the Chernoff-based transformation matrix estimation method for on-line learning in Bayesian binary hypothesis tests

Lorenzo-García, F. D., Navarro-Mesa, J. L., & Ravelo-García, A. G. (2007) · Acceda (Universidad de Las Palmas de Gran Canaria)

Introduction

Liu, H., Chen, C., Li, Y., Duan, Z., & Li, Y. (2022) · Elsevier eBooks · doi:10.1016/b978-0-323-90588-6.00001-9

Report on scipost_202109_00014v1

(2021) · SciPost Physics · doi:10.21468/scipost.report.3771

Report on scipost_202109_00014v1

(2021) · SciPost Physics · doi:10.21468/scipost.report.3693

Improving Utterance Rewriter Based on MMI and Text Data Augmentation

Yang, L., Lin, H., Li, W., Meng, Z., Wang, P. S. P., Li, X., & Luo, H. (2022) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s021800142259011x

Multimodal Learning with Vision and Language

(2019) · International Conference on Image Processing Theory, Tools and Applications (IPTA) · doi:10.1109/ipta.2019.8936104

References

Larsen, E., & Aarts, R. M. (2004) · doi:10.1002/0470858710.refs

Detecting Regional Events via Statistical Analysis of Geodetic Networks

Granat, R. A. (2007) · Birkhäuser Basel eBooks · doi:10.1007/978-3-7643-8131-8_17

Optimal generative and discriminative acoustic model training for speech recognition

Joshi, N. (2021) · doi:10.32920/ryerson.14664396

New methodology for the integration of biometric features in speaker recognition systems applied to security environments

Fernández, L. M. M. (2014) · doi:10.20868/upm.thesis.33122

A GA-like Dynamic Probability Method with Mutual Information for Feature SelectionPreprint

Wang, G., Lauri, F., & Hassani, A. H. E. (2023) · Research Square · doi:10.21203/rs.3.rs-3120809/v1

On classification improvement by using an approximate discriminative hidden Markov model

Carvajal, J., Sarria-Paja, M., & Castellanos-Dominguez, G. (2013) · Revista Facultad de Ingeniería Universidad de Antioquia · doi:10.17533/udea.redin.14726

Applying Learning Analytics Approaches to Detect and Track Students' Cognitive States During Virtual Problem-Solving Activities

Pan, Z., Li, C., Zou, W., & Liu, M. (2023) · Advances in educational technologies and instructional design book series · doi:10.4018/978-1-6684-9527-8.ch002

Evaluation and Analysis of Minimum Phone Error Training and Its Modified Versions for Large Vocabulary Mandarin Speech Recognition

Cheng, Y.-J., Lin, C., & Lee, L.-S. (2008) · International Symposium on Chinese Spoken Language Processing (ISCSLP) · doi:10.21437/iscslp.2008-28

Investigating The Effect of Language Models in Sequence Discriminative Training For Neural Transducers

Yang, Z. G., Zhou, W. G., Schlüter, R., & Ney, H. (2023) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru57964.2023.10389683

Max-Margin Transducer Loss: Improving Sequence-Discriminative Training Using a Large-Margin Learning Strategy

Swaminathan, R. V., Strimel, G. P., Rastrow, A., Mallidi, S. H., Zhen, K., Nguyen, H. D., Susanj, N., & Mouchtaris, A. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446322

On the Relation Between Internal Language Model and Sequence Discriminative Training for Neural Transducers

Yang, Z. G., Zhou, W. G., Schlüter, R., & Ney, H. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10447468

A NEW METHOD FOR THE ESTIMATION OF HIDDEN MARKOV MODEL PARAMETERS

Uang, T., & Chen, Y. (1991) · Acta Automatica Sinica

MAXIMIZATION OF MUTUAL INFORMATION FOR TRAINING HIDDEN MARKOV MODELS IN SPEECH RECOGNITION

Giurgiu, M. (2015)

A new algorithm for the estimation of hidden Markov model parameters

Bahl, L. R., Brown, P. F., de Souza, P. V., & Mercer, R. L. (2003) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.1988.196627 · Cited by 116

Estimating hidden Markov model parameters so as to maximize speech recognition accuracy

Bahl, L. R., Brown, P. F., de Souza, P. V., & Mercer, R. L. (1993) · IEEE Transactions on Speech and Audio Processing · doi:10.1109/89.221369 · Cited by 56

Training of Hidden Markov Parameters using Mutual Information and Its Application to Speech Recognition

N.S.Kim, & Un, C. K. (1990) · 한국음향학회지= The journal of the acoustical society of Korea