Blog
About

4
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Sequence Discriminative Training for Deep Learning based Acoustic Keyword Spotting

      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

          Speech recognition is a sequence prediction problem. Besides employing various deep learning approaches for framelevel classification, sequence-level discriminative training has been proved to be indispensable to achieve the state-of-the-art performance in large vocabulary continuous speech recognition (LVCSR). However, keyword spotting (KWS), as one of the most common speech recognition tasks, almost only benefits from frame-level deep learning due to the difficulty of getting competing sequence hypotheses. The few studies on sequence discriminative training for KWS are limited for fixed vocabulary or LVCSR based methods and have not been compared to the state-of-the-art deep learning based KWS approaches. In this paper, a sequence discriminative training framework is proposed for both fixed vocabulary and unrestricted acoustic KWS. Sequence discriminative training for both sequence-level generative and discriminative models are systematically investigated. By introducing word-independent phone lattices or non-keyword blank symbols to construct competing hypotheses, feasible and efficient sequence discriminative training approaches are proposed for acoustic KWS. Experiments showed that the proposed approaches obtained consistent and significant improvement in both fixed vocabulary and unrestricted KWS tasks, compared to previous frame-level deep learning based acoustic KWS methods.

          Related collections

          Most cited references 21

          • Record: found
          • Abstract: found
          • Article: found
          Is Open Access

          Speech Recognition with Deep Recurrent Neural Networks

          Recurrent neural networks (RNNs) are a powerful model for sequential data. End-to-end training methods such as Connectionist Temporal Classification make it possible to train RNNs for sequence labelling problems where the input-output alignment is unknown. The combination of these methods with the Long Short-term Memory RNN architecture has proved particularly fruitful, delivering state-of-the-art results in cursive handwriting recognition. However RNN performance in speech recognition has so far been disappointing, with better results returned by deep feedforward networks. This paper investigates \emph{deep recurrent neural networks}, which combine the multiple levels of representation that have proved so effective in deep networks with the flexible use of long range context that empowers RNNs. When trained end-to-end with suitable regularisation, we find that deep Long Short-term Memory RNNs achieve a test set error of 17.7% on the TIMIT phoneme recognition benchmark, which to our knowledge is the best recorded score.
            Bookmark
            • Record: found
            • Abstract: not found
            • Conference Proceedings: not found

            Purely Sequence-Trained Neural Networks for ASR Based on Lattice-Free MMI

              Bookmark
              • Record: found
              • Abstract: not found
              • Conference Proceedings: not found

              Small-footprint keyword spotting using deep neural networks

                Bookmark

                Author and article information

                Journal
                01 August 2018
                Article
                1808.00639

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

                Custom metadata
                68T10
                accepted by Speech Communication, 08/02/2018
                cs.CL

                Theoretical computer science

                Comments

                Comment on this article