Edinburgh Research Explorer

An articulatory feature-based tandem approach and factored observation modeling

Research output: Chapter in Book/Report/Conference proceedingConference contribution

  • O Cetin
  • A. Kantor
  • S. King
  • C. Bartels
  • M. Magimai-Doss
  • J. Frankel
  • K. Livescu

Related Edinburgh Organisations

Open Access permissions

Open

Documents

  • Download as Adobe PDF

    Rights statement: © Cetin, O., Kantor, A., King, S., Bartels, C., Magimai-Doss, M., Frankel, J., & Livescu, K. (2007). An articulatory feature-based tandem approach and factored observation modeling. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, 2007 (ICASSP 2007). (Vol. 4, pp. 645-648). 10.1109/ICASSP.2007.366995

    Accepted author manuscript, 48 KB, PDF-document

Original languageEnglish
Title of host publicationProceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, 2007 (ICASSP 2007)
Pages645-648
Number of pages4
Volume4
DOIs
Publication statusPublished - 1 Apr 2007

Abstract

The so-called tandem approach, where the posteriors of a multilayer perceptron (MLP) classifier are used as features in an automatic speech recognition (ASR) system has proven to be a very effective method. Most tandem approaches up to date have relied on MLPs trained for phone classification, and appended the posterior features to some standard feature hidden Markov model (HMM). In this paper, we develop an alternative tandem approach based on MLPs trained for articulatory feature (AF) classification. We also develop a factored observation model for characterizing the posterior and standard features at the HMM outputs, allowing for separate hidden mixture and state-tying structures for each factor. In experiments on a subset of Switchboard, we show that the AFbased tandem approach is as effective as the phone-based approach, and that the factored observation model significantly outperforms the simple feature concatenation approach while using fewer parameters.

Download statistics

No data available

ID: 2075125