Home | Legals | Sitemap | KIT

Neural Network Publications

 

Journals 

 

1.       “Multimodal Interfaces”, A. Waibel, M. Vo, P. Duchnowski, and S. Manke, AI Review Journal, book: 145-165, journal: 299-319, 1996. 

 

2.         “The Meta-Pi Network: Building Distributed Knowledge Representations for Robust Multi-Source Pattern Recognition”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992.

 

3.         “Integrated Phoneme and Function Word Architecture of Hidden Control Neural Networks for Continuous Speech Recognition”, B. Petek, A. Waibel, J. Tebelskis, Speech Communications, pp. 273-282, Vol. 11, Nos. 2-3, June, 1992.

 

4.     “Connectionist Approaches to Large Vocabulary Continuous Speech Recognition”, H. Sawai, Y. Minami, M. Miyatake, A. Waibel, K. Shikano, Transactions of the IEICE, Special Issue on Continuous Speech Recognition and Understanding, Vol. E 74, No. 7, July, 1991.    


5.          “Connectionist Large Vocabulary Speech Recognition”, A. Waibel, Special issue on Neural Networks, Transactions of the Institute of Electronics, Information and Communication Engineers (Japan), November, 1990 (invited paper).

 

6.         “A Novel Objective Function for Improved Phoneme Recognition Using Time-Delay Neural Networks”, J. Hampshire, A. Waibel, IEEE, Transactions on Neural Networks, June, Vol. 1, No. 2, 1990.

 

7.         “A Time-Delay Neural Network Architecture for Isolated Word Recognition”, Kevin J. Lang, Alex H. Waibel, Geoffrey E. Hinton, Neural Networks, pp. 22-42, Vol. 3, Issue 1, 1990.

 

8.         “Modularity and Scaling in Large Phonemic Neural Networks”, A. Waibel, H. Sawai, K. Shikano. IEEE Transactions on Acoustics, Speech and Signal Processing, December, December 1989.

 

9.         “Modular Neural Networks for Speech Recognition”, A. Waibel and J. Hampshire, BYTE Magazine, August, 1989 (invited paper).

 

10.         “Phoneme Recognition Using Time-Delay Neural Networks”, A. Waibel, T. Hanazawa, G. Hinton, K. Shikano, K. Lang, IEEE Transactions on Acoustics, Speech and Signal Processing, Vol. 37, No. 3, March, 1989.

 

11.      “Modular Construction of Time-Delay Neural Networks for Speech Recognition”, A. Waibel, Journal for Neural Computation, MIT Press Journals, Number 1, March, 1989.

 

 

 

Books, Bookchapters

 

1.         “Time-Delay Neural Networks and NN/HMM Hybrids: A Family of Connectionist Continuous-Speech Recognition Systems”, J. Fritsch, H. Hild, U. Meier, A. Waibel, in: Handbook of Neural Networks for Speech Processing, Chapter 7, Artech House, 2000.

 

2.         “Applying Divide and conquer to large scale pattern recognition tasks”, Jürgen Fritsch, Michael Finke, Springer Book, 1997

 

3.         “The Use of Dynamic Writing Information in a Connectionist On-Line Cursive Handwriting Recognition System”, S.Manke, M. Finke and A. Waibel, in: Advances in Neural Information Processing Systems, 1995, Morgan Kaufmann.

 

4.       “Phoneme Recognition Using Time-Delay Neural Networks”, A. Waibel, in: Back-Propagation: Theory, Architectures and Applications, Y. Chauvin and D. Rumelhart, Editors, Lawrence Erlbaum, 1995.

 

5.         “Performance through Consistency: MS-TDNN’s for Large Vocabulary Continuous Speech Recognition”, Joe Tebelskis and Alex Waibel, n: Advances in Neural Information Processing Systems, 1993, Morgan Kaufmann.

 

6.         “Connected Letter Recognition with a Multi-State Time Delay Network”, H. Hild, A. Waibel, in: Advances in Neural Information Processing Systems, 1993, Morgan Kaufmann.

 

7.          “Multi-State Time Delay Neural Networks for Continuous Speech Recognition”, P. Haffner, A. Waibel, in: Advances in Neural Information Processing Systems, 1992, Morgan Kaufmann.

 

8.         “Neural Network Applications to Speech”, A. Waibel and J. Hampshire, in: Neural Networks, Concepts, Applications and Applications, Vol. 1, Antognetti and Milutinovic, Editors, Prentice Hall Publishers, Englewood Cliffs, NJ, 1991.

 

9.         “Continuous Speech Recognition by Linked Predictive Neural Networks”, in: Advances in Neural Information Processing Systems, 1991, Morgan Kaufmann.

 

10.         “The Tempo 2 Algorithm: Adjusting Time-Delays by Supervised Learning”, U. Bodenhausen, A. Waibel, in: Advances in Neural Information Processing Systems, 1991, Morgan Kaufmann.

 

11.         “Neural Networks Approaches for Speech Recognition”, A. Waibel, In: Advances in Speech Signal Processing, Furui, S. and Sondhi, M. (editors), Chapter 4, Marcel Dekker Inc., 1991.

 

12.      “Connectionist Large Vocabulary Speech Recognition”, A. Waibel, Proceedings of the NATO Advanced Study Institute, Speech Recognition and Understanding. Recent Advances, Trends and Applications, Springer Verlag, 1990.

 

13.      “Incremental Parsing by Modular Recurrent Connectionist Networks”, A. Jain and A. Waibel. in: Advances in Neural Information Processing Systems, 1990, Morgan Kaufmann.

 

14.       “Connectionist Architectures for Multi-Speaker Phoneme Recognition”, J. Hampshire and A. Waibel. in: Advances in Neural Information Processing Systems, 1990, Morgan Kaufmann.

 

15.      “Phoneme Recognition Using Time-Delay Neural Networks”, A. Waibel, T. Hanazawa, G. Hinton, K. Shikano, K. Lang, in: Readings in Speech Recognition, A. Waibel, K.F. Lee (eds.), 1990, Morgan Kaufmann.

 

16.      “Consonant Recognition by Modular Construction of Large Phonemic Time-Delay Neural Networks”, A. Waibel, H. Sawami, K. Shikano, in: Readings in Speech Recognition, A. Waibel, K.F. Lee (eds.), 1990, Morgan Kaufmann.

 

17.      “Speech Recognition by Neural Networks”, A. Waibel and J. Hampshire, In: The 1989 Genoa Summer School, Prentice-Hall, 1989.

 

18.      “Modularity in Neural Networks for Speech Recognition”, A. Waibel. in: Advances in Neural Information Processing Systems, Volume I, 1989, Morgan Kaufmann.

 

 

 

Conference Papers

 

1.         “The 2015 KIT IWSLT Speech-to-Text Systems for English and German”, Markus Müller, Thai-Son Nguyen, Matthias Sperber, Kevin Kilgour, Sebastian Stüker, Alex Waibel, Proceedings of the 12th International Workshop on Spoken Language Translation (IWSLT), Da Nang, Vietnam, December 3-4, 2015.

 

2.         “Using Language Adaptive Deep Neural Networks for Improved Multilingual Speech Recognition.pdf”, Markus Müller, Alex Waibel, Proceedings of the 12th International Workshop on Spoken Language Translation (IWSLT), Da Nang, Vietnam, December 3-4, 2015.

 

3.         “Gaussian Free Cluster Tree Construction using Deep Neural Network”, Linchen Zhu, Kevin Kilgour, Sebastian Stüker, Alex Waibel, Proceedings of the 16th Annual Conference of the International Speech Communication Association (INTERSPEECH), Dresden, Germany, September 6-10, 2015.

 

4.         “Combination of NN and CRF Models for Joint Detection of Punctuation and Disfluencies”, Eunah Cho, Kevin Kilgour, Jan Niehues, Alex Waibel, Proceedings of the 16th Annual Conference of the International Speech Communication Association (INTERSPEECH), Dresden, Germany, September 6-10, 2015.

 

5.         “Using Neural Networks for Data-driven Backchannel Prediction: A Survey on Input Features and Training”, Markus Müller, David Leuschner, Lars Briem, Maria Schmidt, Kevin Kilgour, Sebastian Stüker, and Alex Waibel, 2nd International Conference on Learning and Collaboration Technologies in association with HCI International 2015, Los Angeles, California, USA, August 2-7, 2015.

 

6.         “Lexical Translation Model Using a Deep Neural Network Architecture”, Thanh-Le Ha, Jan Niehues, Alexander Waibel, Proceedings of the 11th International Workshop on Spoken Language Translation (IWSLT), Lake Tahoe, USA, December 4-5, 2014.

 

7.         “Combining Techniques from different NN-based Language Models for Machine Translation”, Jan Niehues, Alexander Allauzen, Francois Yvon, Alex Waibel, The eleventh biennial Conference of the Association for Machine Translation in the Americas (AMTA), Vancouver, Canada, October 22 - 26, 2014.

 

8.         “Neural Network Language Models for Low Resource Languages”, Ankur Gandhe, Florian Metze, Ian Lane, Proceedings of the 15th Annual Conference of the International Speech Communication Association (INTERSPEECH 2014), Singapore, September 14-18, 2014.

 

9.         “Towards Speaker Adaptive Training of Deep Neural Network Acoustic Models”, Yajie Miao Hao Zhang, Florian Metze, Proceedings of the 15th Annual Conference of the International Speech Communication Association (INTERSPEECH 2014), Singapore, September 14-18, 2014.

 

10.         “Improving Language Universal Feature Extractions with Deep Maxout and Convolutional Neural Networks”, Yajie Miao, Florian Metze, Proceedings of the 15th Annual Conference of the International Speech Communication Association (INTERSPEECH 2014), Singapore, September 14-18, 2014.

 

11.         “Distributed Learning of Multilingual DNN Feature Extractors Using GPUS”, Yajie Miao, Hao Zhang, Florian Metze, Proceedings of the 15th Annual Conference of the International Speech Communication Association (INTERSPEECH 2014), Singapore, September 14-18, 2014.

 

12.         “Optimization of Neural Network Language Models for Keyword Search”, Ankur Gandhe, Florian Metze, Alex Waibel, Ian Lane, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) Florence, Italy, May 4-9, 2014.

 

13.         “Modular Combination of Deep Neural Networks for Acoustic Modeling”, J. Gehring, W. Lee, K. Kilgour, I. Lane, Y. Miao, A. Waibel, Proceedings of the 14th Annual Conference of the International Speech Communication Association (INTERSPEECH 2013), Lyon, France, 2013.

 

14.         “Improved feature processing for Deep Neural Networks”, S. Rath, D. Povey, D. Vesely, J. Cernocky, Proceedings of the 14th Annual Conference of the International Speech Communication Association (INTERSPEECH 2013), Lyon, France, 2013.

 

15.         “Sequence-discriminative training of deep neural networks”, K. Vesely, A. Ghosal, L. Burget, D. Povey, Proceedings of the 14th Annual Conference of the International Speech Communication Association (INTERSPEECH 2013), Lyon, France, 2013.

 

16.         “Improving Low-Resource CD-DNN-HMM using Dropout and Multilingual DNN Training”, Yajie Miao, Florian Metze, Proceedings of the 14th Annual Conference of the International Speech Communication Association (INTERSPEECH 2013), Lyon, France, 2013.

 

17.         “Deep Maxout Networks for Low-Resource Speech Recognition”, Yajie Miao, Florian Metze, Shourabh Rawat, Automatic Speech Recognition and Understanding Workshop, ASRU 2013, Olomouc Czech Republic, Dec. 8-12, 2013.

 

18.         “DNN Acoustic Modeling With Modular Multi-Lingual Feature Extraction Networks”, Jonas Gehring, Quoc Bao Nguyen, Florian Metze, Alex Waibel, Automatic Speech Recognition and Understanding Workshop, ASRU 2013, Olomouc Czech Republic, Dec. 8-12, 2013.

 

19.         “Optimizing Deep Bottleneck Feature Extraction”, Quoc Bao, Jonas Gehring, Kevin Kilgour, Alex Waibel, The 10th IEEE RIVF International Conference on Computing and Communication Technologies, Hanoi, Nov. 10-13, 2013.

 

20.         “Comparing RNNS and Log-Linear Interpolation of Improved Skip Model on four Babel Languages: Cantonese, Pashto, Tagalog, Turkish”, Mittul Singh, Dietrich Klakow, Proceedings of the 2013 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), May 26-31, 2013.

 

21.         “Neural Network-based Head Pose Estimation and Multi-view Fusion”, Michael Voit, Kai Nickel, Rainer Stiefelhagen, CLEAR Evaluation Workshop 2006, Southampton, UK, April 2006.

 

22.         “Multi-view Head Pose Estimation using Neural Networks”, Michael Voit, Kai Nickel, Rainer Stiefelhagen, Face Processing in Video 2005, FPiV 2005, Victoria, British Columbia, Canada, May 2005.

 

23.         “Estimating Head Pose with Neural Networks - Results on the Pointing04 ICPR Workshop Evaluation Data”, Rainer Stiefelhagen, Pointing '04 ICPR workshop 2004, ICPR 2004, Cambridge, UK, August 22, 2004.

 

24.        Modeling and efficient decoding of large vocabulary conversational speech", Michael Finke, Jürgen Fritsch, Detlef Koll, Alex Waibel, Eurospeech, 1999

 

25.         “HMM and Neural Networks Based Speech Act Detection”, Klaus Ries, International Conference on Acoustics and Signal Processing, ICASSP 1999, Phoenix, Arizona, USA, March 1999.

 

   26.       "Hierarchies of Neural Networks for Connectionist Speech Recognition", J. Fritsch, Alex Waibel, ESANN, 1998

 

 

   27.       "ACID/HNN: Clustering Hierarchies of Neural Networks for Context-Dependent Connectionist Acoustic Modeling", J.

             Fritsch, Michael Finke, ICASSP, 1998

 

   28.      "Effective Structural Adaptation of LVCSR Systems to unseen Domains using Hierarchical Connectionist Acoustic

             Models", J. Fritsch, M. Finke, A. Waibel, ICSLP, 1998

 

   29.      "ACID/HNN: A Framework for Hierarchical Connectionist Acoustic Modeling", J. Fritsch, ASRU 1997

 

30.        “Adaptively Growing Hierarchical Mixtures of Experts”, J. Fritsch, M. Finke and A. Waibel, NIPS Conference 96, Denver Colorado, USA, Dec 2-10, 1996.

 

31.          “Recognition of Spelled Names Over The Telephone”, H. Hild and A. Waibel, in Proceedings of the International Conference on Speech and Language Processing (ICSLP ‘96), Philadelphia, USA, Oct 3-6, 1996.

 

32.         “A Fast Search Technique for Large Vocabulary On-Line Handwriting Recognition”, S. Manke, M. Finke and A. Waibel, International Workshop on Frontiers in handwriting Recognition, University of Essex, Colchester, England, September 2-5, 1996.

 

33.         “A Model-Based Gaze-Tracking System”, R. Stiefelhagen, J. Yang and A. Waibel, Proceedings of Joint Symposia on Intelligence and Systems, Washington, DC, November 1996.

 

34.         “Toward Movement-Invariant Automatic Lip-Reading and Speech Recognition”, P. Duchnowski, M. Hunke, D.      Busching, U. Meier, and A. Waibel, Proceedings of the 1995 International Conference on Acoustics, Speech, and   Signal Processing (ICASSP), Detroit, Michigan, May 1995.

 

35.         “NPen++: A Writer Independent, Large Vocabulary On-Line Cursive Handwriting Recognition System”, S. Manke,  M. Finke, and A. Waibel, Proceedings of the International Conference on Document Analysis and Recognition, IEEE Computer Society, Montreal, Canada, August 1995.

 

36.         "Integrating Spelling into Spoken Dialogue Recognition”, H. Hild and A. Waibel, pp.1977-1979, vol. 3, Proceedings

               of Eurospeech ‘95, Madrid, Spain, September 1995.         

 

37.         “A Connectionist Recognizer for On-Line Cursive Handwriting Recognition”, S.Manke and U.Bodenhausen, IEEE Proceedings International Conference on Acoustics, Speech, and Signal Processing, Adelaide, Australia, 1994.

 

38.      “Learning Complex Output Representations in Connectionist Parsing of Spoken Language”, F. Buo, T. Polzin and A. Waibel, IEEE Proceedings International Conference on Acoustics, Speech, and Signal Processing, Adelaide, Australia, 1994.

 

39.      “Incremental Learning Using the Time Delay Neural Network”, M. T. Vo, IEEE Proceedings International Conference on Acoustics, Speech, and Signal Processing, Adelaide, Australia, 1994.

 

40.      “Connectionist Models in Multimodal Human-Computer Interaction”, A. Waibel and P. Duchnowski, Proceedings of GOMAC’94, San Diego, November 1994.

 

41.      “Speaker-Independent Connected Letter Recognition with a Multi-State Time Delay Neural Network”, H. Hild and A. Waibel, pp. 1481-1485, Proceedings of Eurospeech’93, Berlin, 1993.

 

42.      “Tuning by Doing”, U. Bodenhausen and A. Waibel, pp. 1485-1488, Proceedings of Eurospeech’93, Berlin, 1993.

 

43.      “Application Oriented Automatic Structuring of Time-Delay Neural Networks for High Performance Character and Speech Recognition”, U. Bodenhausen and A. Waibel, In: Proceedings ICNN 93, San Francisco, March 1993.

 

44.      “Bimodal Sensor Integration on the Example of Speech-Reading”, C. Bregler, S. Manke, H. Hild, and A. Waibel, In: Proceedings ICNN 93, San Francisco, March 1993.

 

45.      “Improving Connected Letter Recognition by Lipreading”, C. Bregler, H. Hild, S. Manke, and A. Waibel, IEEE Proceedings International Conference on Acoustics, Speech, and Signal Processing, Minneapolis, 1993.

 

46.      “Multi-Speaker/Speaker-Independent Architectures for the Multi-State Time Delay Neural Network”, H. Hild, A Waibel, IEEE Proceedings International Conference on Acoustics, Speech, and Signal Processing, ICASSP 1993, Minneapolis, 1993.

 

47.      “Flexibility through Incremental Learning: Neural Networks for Text Categorization”, P. Geutner, U. Bodenhausen and A. Waibel, Proceedings of the World Congress on Neural Networks, WCNN 1993, Portland, July, 1993.

 

48.       “Testing Generality In Janus: A Multi-Lingual Speech Translation System”, Louise Osterholtz, Joe Tebelskis, Ivica Rogina, Hiroaki Saito, Charles Augustine, Arthur McNair, Alex Waibel, Monika Woszczyna, Tilo Sloboda, IEEE International Conference on Acoustics, Speech, and Signal Processing 1992, ICASSP 1992, San Francisco, USA.

 

49.       “JANUS Speech-to-Speech Translation Using Connectionist and Non-Connectionist Techniques”, A. Jain, A. McNair, J. Tebelskis, A. Hauptmann, H. Saito, A. Waibel, Advances in Neural Information Processing systems 1992.

 

50.       “A Hybrid Neural Network, Dynamic Programming Word Spotter”, T. Zeppenfeld, A Waibel, IEEE Proceedings International Conference on Acoustics, Speech, and Signal Processing, San Francisco, 1992.

 

51.      “PARSEC: A Structured Connectionist Parsing System for Spoken Language”. A. N. Jain, A. Waibel, and D. S. Touretzky, IEEE Proceedings International Conference on Acoustics, Speech, and Signal Processing, San Francisco, 1992.

 

52.      “Continuous Speech Recognition with the Connectionist Viterbi Training Procedure: A Summary of Recent Work”, M.A. Franzini, A. Waibel and K.F. Lee, Proceedings of the IEEE International Joint Conference on Neural Networks. Singapore: November, 1991.

 

53.      “Effectiveness of the Neural Fuzzy Training Method for Continuous Speech Recognition”, Y. Komori, K.Fukuzawa, M.Sugiyama, A.H.Waibel, S.Sagayama, Acoustic Society of Japan, Fall-meeting, 2-5-11, 1991-10.

 

54.      “An Improvement of TDNN-LR Continuous Speech Recognition System Using a Neural Fuzzy Training Approach”, Y. Komori, A.H. Waibel, S. Sagayama, Proceedings of the IEICE workshop, SP91-24, pp. 49-56, 1991-06.

 

55.      “A New Fuzzy Training Method for Phoneme Identification Neural Networks”, Y.Komori, A.H.Waibel, S.Sagayama, Acoustic Society of Japan, Spring-meeting, 1-5-15, pp. 33-34, 1991-03.

 

56.      “Time-Delay Neural Networks Embedding Time Alignment: A Performance Analysis”, P. Haffner, A. Waibel, Proceedings of Eurospeech, Genoa, 1991.

 

57.      “Integrated Phoneme-Function Word Architecture of Hidden Control Neural Networks for Continuous Speech Recognition”, B. Petek, A. Waibel and J. Tebelskis, Proceedings of Eurospeech, Genoa, Italy, September 1991.

 

58.      “Recent Work in Continuous Speech Recognition using the Connectionist Viterbi Training Procedure.”, M.A. Franzini, A. Waibel and K.F. Lee, Proceedings of EUROSPEECH. Genoa, Italy, September 1991.

 

59.      “Evaluation of Speaker-Independent Phoneme Recognition on TIMIT Database Using Integrated Time-Delay Neural Networks”, N. Hataoka, A. Waibel, Proceedings of Eurospeech, Genoa, 1991.

 

60.      “Speaker-Independent Phoneme Recognition on TIMIT Database Using Integrated Time-Delay Neural Networks”, N. Hataoka, A. Waibel, Proceedings of Eurospeech, Genoa, 1991.

 

61.      “Review of TDNN (Time-Delay Neural Network) Architectures for Speech Recognition”, M. Sugiyama, H. Sawai, A. Waibel, Proceedings of the ICPS, 1991.

 

62.      Connectionist Speaker Normalization and its Applications to Speech Recognition”, X.D. Huang, K.F. Lee, A. Waibel, Proceedings of the IEEE-SP Workshop on Neural Networks for Signal Processing, Princeton, October, 1991.

 

63.      “Learning the Architecture of Neural Networks for Speech Recognition”, U. Bodenhausen, A. Waibel, Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Toronto, May, 1991.

 

64.      “A Connectionist Model for Dialog Processing”, Y-Y. Wang, A.Waibel, Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Toronto, May, 1991.

 

65.      “Continuous Speech Recognition Using Linked Predictive Neural Networks”, J. Tebelskis, A. Waibel, B. Petek, Otto Schmidbauer, Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Toronto, May, 1991.

 

66.      “Integrating Time Alignment and Neural Networks for High Performance Continuous Speech Recognition”, A. Haffner, M. Franzini, A. Waibel, Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Toronto, May, 1991.

 

67.      “JANUS: A Speech-to-Speech Translation System Using Connectionist and Symbolic Processing Strategies”, A. Waibel, A. Jain, A. McNair, H. Saito, A. Hauptmann, J. Tebelskis, Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Toronto, May, 1991.

 

68.      “Connectionist Large Vocabulary Speech Recognition”, A. Waibel, Proceedings of InfoJapan’90, the 30 meeting of the Information Processing Society of Japan, October, 1990.

 

69.      “Phoneme-Based Word Recognition by Neural Network - A Step Toward Large Vocabulary Recognition”, A. Hirai and A. Waibel, Proceedings of the International Joint Conference on Neural Networks, ICNN 1990, June 17-21, 1990.

 

70.      “Speaker-Independent Phoneme Recognition on TIMIT Database Using Integrated Time-Delay Neural Networks”, N. Hataoka, A. Waibel, Proceedings of the International Joint Conference on Neural Networks, ICNN 1990, June 17-21, 1990.

 

71.      “Robust Connectionist Parsing of Spoken Language”, A. Jain and A. Waibel, Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Albuquerque, April, 1990.

 

72.      “Connectionist Viterbi Training”, M. Franzini, K.F. Lee and A. Waibel, Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Albuquerque, April, 1990.

 

73.      “The Meta-Pie Network: Connectionist Rapid Adaptation for High-Performance Multi-Speaker Phoneme Recognition”, J. Hampshire and A. Waibel, Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Albuquerque, April, 1990.

 

74.      “Large Vocabulary Recognition Using Linked Predictive Neural Networks”, J. Tebelskis and A. Waibel, Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Albuquerque, April, 1990.

 

75.      “Speech Recognition Using Sub-Phoneme Recognition Neural Network”, K. Aikawa and A. Waibel, Proceedings of the International Conference on Spoken Language Processing, 1990.

 

76.      “Fast Back-Propagation Learning Methods for Neural Networks in Speech”, P. Haffner, A. Waibel, K. Shikano, Proceedings of the European Conference on Speech Technology, Paris, September, 1989.

 

77.      “A Connectionist Parser Aimed at Spoken Language”, A. Jain and A. Waibel, Proceedings of the International Workshop on Parsing Technologies”, August, 1989, Carnegie Mellon University.

 

78.      “A Novel Objective Function for Improved Phoneme Recognition Using Time-Delay Neural Networks”, J. Hampshire, A. Waibel, Proceedings of the 1989 International Joint Conference on Neural Networks, June, 1989.

 

79.      “Consonant Recognition by Modular Construction of Large Phonemic Time-Delay Neural Networks”, A. Waibel, H. Sawai, K. Shikano, Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Glasgow, May, 1989.

 

80.      “Spotting Japanese CV-Syllables and Phonemes Using Time-Delay Neural Networks”, H. Sawai, A. Waibel, M. Miyatake, K. Shikano, Proceedings of the International Conference on Acoustics, Speech and Signal Processing, Glasgow, May, 1989.

 

81.      “Phoneme Recognition by Scaling up Modular Time-Delay Neural Networks”, H.Sawai, A. Waibel, M. Miyatake, K. Shikano, SP88-105, Meeting of the Institute of Electrical, Information and Communication Engineers (IEICE), December, 1988, Japan, pp. 73-80.

 

82.      “Fast Back-Propagation Learning Methods for Neural Networks in Speech”, P. Haffner, A. Waibel, K. Shikano, 2-P-11, Proceedings of the Fall Meeting of the Acoustical Society of Japan, October, 1988.

 

83.      “Phoneme Recognition by Modular Construction of Time-Delay Neural Networks”, A. Waibel, H. Sawai, K. Shikano, 2-P-12, Proceedings of the Fall Meeting of the Acoustical Society of Japan, October, 1988.

 

84.      “A Preliminary Study on Spotting Japanese CV-Syllables by Time-Delay Neural Networks”, H. Sawai, A. Waibel, K. Shikano, 2-P-11, Proceedings of the Fall Meeting of the Acoustical Society of Japan, October, 1988.

 

85.      “Connectionist Glue: Modular Design of Neural Speech Systems”, A. Waibel, in: D.S. Touretzky and G.E. Hinton, Proceedings of the 1988 Connectionist Models Summer School. Morgan Kaufmann, 1988.

 

86.      “Noise Reduction by Connectionist Models”, S. Tamura and A. Waibel, Proceedings of the International Conference on Acoustics, Speech and Signal Processing, New York, NY, April, 1988.

 

87.      “Phoneme Recognition: Neural Networks vs. Hidden Markov Models” A. Waibel, T. Hanazawa, G. Hinton, K. Shikano, K. Lang, Proceedings of the International Conference on Acoustics, Speech and Signal Processing, New York, NY, April, 1988.

 

88.      “Noise Reduction through Waveform Input and Output Using Neural Networks”, S. Tamura and A. Waibel, SP87-112, Spring Meeting of the Acoustical Society of Japan, March, 1988, Japan.

 

89.      “Noise Reduction by Neural Networks”, T. Tamura and A. Waibel, SP87-112, Meeting of the Institute of Electrical, Information and Communication Engineers (IEICE), January, 1988, Osaka, Japan.

 

90.      “Phoneme Recognition Using Time-Delay Neural Networks”, A. Waibel, Proceedings of The First Symposium on Advanced Man-Machine Interface Through Spoken Language, January, 1988, Gakushikaikan, Tokyo, Japan.

 

91.      “Phoneme Recognition Using Time-Delay Neural Networks”, A. Waibel, SP87-100, Meeting of the Institute of Electrical, Information and Communication Engineers (IEICE), December, 1987, Tokyo, Japan.

 

92.      “Phoneme Recognition Using Time-Delay Neural Networks”, A. Waibel, T. Hanazawa, G. Hinton, K. Shikano, K. Lang. ATR Technical Report, TR-I-0006, 1987.

 

 

 

Further Articles

 

 1.     “Neural Network approach to word category prediction for english texts”, M. Nakamura, K. Maruyama, T. Kawabata and K. Shikano, ATR Interpreting Telephony Research Laboratories, Kyoto 619-02, Japan

 

 2.     “A study of English word category prediction based on neural networks”, IEEE Proceedings of the ICASSP Glasgow Scotland, 1989

 

 

All ISL-Publications