18
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Speaker Cluster-Based Speaker Adaptive Training for Deep Neural Network Acoustic Modeling

      Preprint
      ,

      Read this article at

      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.

          Abstract

          A speaker cluster-based speaker adaptive training (SAT) method under deep neural network-hidden Markov model (DNN-HMM) framework is presented in this paper. During training, speakers that are acoustically adjacent to each other are hierarchically clustered using an i-vector based distance metric. DNNs with speaker dependent layers are then adaptively trained for each cluster of speakers. Before decoding starts, an unseen speaker in test set is matched to the closest speaker cluster through comparing i-vector based distances. The previously trained DNN of the matched speaker cluster is used for decoding utterances of the test speaker. The performance of the proposed method on a large vocabulary spontaneous speech recognition task is evaluated on a training set of with 1500 hours of speech, and a test set of 24 speakers with 1774 utterances. Comparing to a speaker independent DNN with a baseline word error rate of 11.6%, a relative 6.8% reduction in word error rate is observed from the proposed method.

          Related collections

          Author and article information

          Journal
          2016-04-20
          Article
          1604.06113
          c25dee69-9446-4923-a999-1e171f608873

          http://arxiv.org/licenses/nonexclusive-distrib/1.0/

          History
          Custom metadata
          Published at IEEE ICASSP 2015
          cs.CL

          Theoretical computer science
          Theoretical computer science

          Comments

          Comment on this article