Combining Knowledge Sources to Reorder N-Best Speech Hypothesis Lists

A simple and general method is described that can combine different knowledge sources to reorder N-best lists of hypotheses produced by a speech recognizer. The method is automatically trainable, acquiring information from both positive and negative examples. In experiments, the method was tested on a 1000-utterance sample of unseen ATIS data.

[1]  Manny Rayner,et al.  Quantitative Evaluation of Explanation-Based Learning as an Optimisation Tool for a Large-Scale Natural Language System , 1991, IJCAI.

[2]  Mari Ostendorf,et al.  Integration of Diverse Recognition Methodologies Through Reevaluation of N-Best Sentence Hypotheses , 1991, HLT.

[3]  Lewis M. Norton,et al.  Recent Improvements and Benchmark Results for Paramax ATIS System , 1992, HLT.

[4]  Pascale Fung,et al.  BBN BYBLOS and HARC February 1992 ATIS Benchmark Results , 1992, HLT.

[5]  Vassilios Digalakis,et al.  A Speech To Speech Translation System Built From Standard Components , 1993, HLT.

[6]  Mitch Weintraub,et al.  Large-vocabulary dictation using SRI's DECIPHER speech recognition system: progressive search techniques , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[7]  Vassilios Digalakis,et al.  Spoken language translation with MID-90's technology: a case study , 1993, EUROSPEECH.

[8]  M-S. Agnas et al,et al.  Spoken Language Translator: First-Year Report , 1994 .

[9]  H. Alshawi,et al.  The Core Language Engine , 1994 .

[10]  Hiyan Alshawi,et al.  Training and Scaling Preference Functions for Disambiguation , 1994, Comput. Linguistics.

[11]  Vassilios Digalakis,et al.  Genones: optimizing the degree of mixture tying in a large vocabulary hidden Markov model based speech recognizer , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.