TR2009-012

A Joint Decoding Algorithm for Multiple-Example-Based Addition of Words To A Pronunciation Lexicon

    •  Bansal, D., Nair, N., Singh, R., Raj, B., "A Joint Decoding Algorithm for Multiple-Example-Based Addition of Words to a Pronunciation Lexicon", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), April 2009.
      BibTeX TR2009-012 PDF
      • @inproceedings{Bansal2009apr,
      • author = {Bansal, D. and Nair, N. and Singh, R. and Raj, B.},
      • title = {A Joint Decoding Algorithm for Multiple-Example-Based Addition of Words to a Pronunciation Lexicon},
      • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
      • year = 2009,
      • month = apr,
      • url = {https://www.merl.com/publications/TR2009-012}
      • }
  • Research Areas:

    Artificial Intelligence, Speech & Audio

Abstract:

We propose an algorithm that enables joint Viterbi decoding of multiple independent audio recordings of a word to derive its pronunciation. Experiments show that this method results in better pronunciation estimation and word recognition accuracy than that obtained either with a single example of the word or using conventional approaches to pronunciation estimation using multiple examples

 

  • Related News & Events

    •  NEWS    ICASSP 2009: 4 publications by Anthony Vetro, Shantanu Rane and others
      Date: April 19, 2009
      Where: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
      MERL Contact: Anthony Vetro
      Brief
      • The papers "A Joint Decoding Algorithm for Multiple-Example-Based Addition of Words to a Pronunciation Lexicon" by Bansal, D., Nair, N., Singh, R. and Raj, B., "One-Handed Gesture Recognition Using Ultrasonic Doppler Sonar" by Kalgaonkar, K. and Raj, B., "A New Method for Tracking Performance Evaluation Based on a Reflective Model and Perturbation Analysis" by Pan, P., Porikli, F. and Schonfeld, D. and "Data Hiding in Hard-Copy Text Documents Robust to Print, Scan, and Photocopy Operations" by Varna, A.L., Rane, S. and Vetro, A. were presented at the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP).
    •