Multilevel discriminative training for spelled word recognition

No abstract is available for this paper.

• Publication year

  1998

• Venue

  Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181)

• Publication date

  1998-05-12

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/ICASSP.1998.674474
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• SmarTspelLTM: a multipass recognition system for name retrieval over the telephone

  1997cited by this paper
• Performance of HMM-based speech recognizers with discriminative state-weights

  1996cited by this paper
• An N-best strategy, dynamic grammars and selectively trained neural networks for real-time recognition of continuously spelled names over the telephone

  1995cited by this paper
• Macrophone: an American English telephone speech corpus for the Polyphone project

  1994cited by this paper
• Speech recognition using weighted HMM and subspace projection approaches

  1994cited by this paper
• Discriminative state-weighting in hidden Markov models

  1994cited by this paper
• The estimation of powerful language models from small and large corpora

  1993cited by this paper
• Minimum error rate training based on N-best string models

  1993cited by this paper
• Segmental GPD training of HMM based speech recognizer

  1992cited by this paper
• A telephone speech database of spelled and spoken names

  1992cited by this paper

• Large Margin Training Improves Language Models for ASR

  2021cites this paper
• Discriminant-function-based minimum recognition error rate pattern-recognition approach to speech recognition

  2000cites this paper
• A new framed-based MCE training strategy for Mandarin LVCSR

  2000cites this paper