fMPE-MAP: improved discriminative adaptation for modeling new domains

No abstract is available for this paper.

• Publication year

  2007

• Venue

  Interspeech

• Publication date

  Unknown publication date

• Fields of study

  Computer Science

• Identifiers
  DOI 10.21437/Interspeech.2007-128
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• The ICSI-SRI Spring 2006 Meeting Recognition System

  2006cited by this paper
• Recent innovations in speech-to-text transcription at SRI-ICSI-UW

  2006cited by this paper
• fMPE: discriminatively trained features for speech recognition

  2005influential reference
• Improved discriminative training using phone lattices

  2005cited by this paper
• Further Progress in Meeting Recognition: The ICSI-SRI Spring 2005 Speech-to-Text Evaluation System

  2005cited by this paper
• Trapping conversational speech: extending TRAP/tandem approaches to conversational telephone speech recognition

  2004cited by this paper
• INCORPORATING TANDEM/HATS MLP FEATURES INTO SRI'S CONVERSATIONAL SPEECH RECOGNITION SYSTEM

  2004cited by this paper
• Voicing feature integration in SRI's decipher LVCSR system

  2004cited by this paper
• MMI-MAP and MPE-MAP for acoustic model adaptation

  2003cited by this paper
• Minimum Phone Error and I-smoothing for improved discriminative training

  2002cited by this paper
• Large scale MMIE training for conversational telephone speech recognition

  2000cited by this paper
• Maximum likelihood linear transformations for HMM-based speech recognition

  1998cited by this paper
• Investigation of silicon auditory models and generalization of linear discriminant analysis for improved speech recognition

  1997cited by this paper

• An Investigation of Deep Neural Networks for Multilingual Speech Recognition Training and Adaptation

  2017cites this paper
• Regularized feature-space discriminative adaptation for robust ASR

  2014influential citation
• Multilingual acoustic models using distributed deep neural networks

  2013cites this paper
• Making themost from multiple microphones in meeting recognition

  2011cites this paper
• Leveraging speaker diarization for meeting recognition from distant microphones

  2010cites this paper
• Unsupervised domain adaptation with multiple acoustic models

  2010cites this paper
• A log-linear discriminative modeling framework for speech recognition

  2010cites this paper
• Multifactor adaptation for Mandarin broadcast news and conversation speech recognition

  2009cites this paper
• The SRI-ICSI Spring 2007 Meeting and Lecture Recognition System

  2007cites this paper