5
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: not found
      • Article: not found

      Exemplar-Based Sparse Representation Features: From TIMIT to LVCSR

      Read this article at

      ScienceOpenPublisher
      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Related collections

          Most cited references23

          • Record: found
          • Abstract: not found
          • Article: not found

          Maximum likelihood linear transformations for HMM-based speech recognition

            Bookmark
            • Record: found
            • Abstract: not found
            • Article: not found

            Speaker-independent phone recognition using hidden Markov models

              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              An application of recurrent nets to phone probability estimation.

              This paper presents an application of recurrent networks for phone probability estimation in large vocabulary speech recognition. The need for efficient exploitation of context information is discussed; a role for which the recurrent net appears suitable. An overview of early developments of recurrent nets for phone recognition is given along with the more recent improvements that include their integration with Markov models. Recognition results are presented for the DARPA TIMIT and Resource Management tasks, and it is concluded that recurrent nets are competitive with traditional means for performing phone probability estimation.
                Bookmark

                Author and article information

                Journal
                IEEE Transactions on Audio, Speech, and Language Processing
                IEEE Trans. Audio Speech Lang. Process.
                Institute of Electrical and Electronics Engineers (IEEE)
                1558-7916
                1558-7924
                November 2011
                November 2011
                : 19
                : 8
                : 2598-2613
                Article
                10.1109/TASL.2011.2155060
                5b96ec27-bd0f-4522-b0a0-4da364792844
                © 2011
                History

                Comments

                Comment on this article