DBLSTM based multilingual articulatory feature extraction for language documentation

No abstract is available for this paper.

• Publication year

  2017

• Venue

  Automatic Speech Recognition & Understanding

• Publication date

  2017-12-01

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.1109/ASRU.2017.8268966
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• English Conversational Telephone Speech Recognition by Humans and Machines

  2017cited by this paper
• Towards phoneme inventory discovery for documentation of unwritten languages

  2017cited by this paper
• Unsupervised Linear Discriminant Analysis for Supporting DPGMM Clustering in the Zero Resource Scenario

  2016cited by this paper
• Towards Improving Low-Resource Speech Recognition Using Articulatory and Language Features

  2016influential reference
• Innovative technologies for under-resourced language documentation: The BULB Project

  2016cited by this paper
• Towards Online-Recognition with Deep Bidirectional LSTM Acoustic Models

  2016cited by this paper
• Language Adaptive DNNs for Improved Low Resource Speech Recognition

  2016cited by this paper
• Theano: A Python framework for fast computation of mathematical expressions

  2016cited by this paper
• The microsoft 2016 conversational speech recognition system

  2016cited by this paper
• Phoneme Boundary Detection using Deep Bidirectional LSTMs

  2016influential reference
• Lasagne: First release.

  2015cited by this paper
• The zero resource speech challenge 2015

  2015cited by this paper
• Using articulatory features and inferred phonological segments in zero resource speech processing

  2015cited by this paper
• A comparison of neural network methods for unsupervised representation learning on the zero resource speech challenge

  2015cited by this paper
• Discovering the phoneme inventory of an unwritten language: A machine-assisted approach

  2014cited by this paper
• Towards speaker adaptive training of deep neural network acoustic models

  2014cited by this paper
• Euronews: a multilingual benchmark for ASR and LID

  2014cited by this paper
• Speaker adaptation of neural network acoustic models using i-vectors

  2013cited by this paper
• Scikit-learn: Machine Learning in Python

  2011cited by this paper
• Information Theoretic Measures for Clusterings Comparison: Variants, Properties, Normalization and Correction for Chance

  2010cited by this paper
• Unsupervised Learning of Acoustic Sub-word Units

  2008cited by this paper
• The fundamental frequency variation spectrum

  2008cited by this paper
• Articulatory Feature-Based Methods for Acoustic and Audio-Visual Speech Recognition: Summary from the 2006 JHU Summer workshop

  2007cited by this paper
• Articulatory features for conversational speech recognition

  2005cited by this paper
• Multilingual articulatory features

  2003cited by this paper
• The German Text-to-Speech Synthesis System MARY: A Tool for Research, Development and Teaching

  2003cited by this paper
• A flexible stream architecture for ASR using articulatory features

  2002cited by this paper
• Evaluation of cross-language voice conversion based on GMM and straight

  2001influential reference
• A one-pass decoder based on polymorphic linguistic context assignment

  2001cited by this paper
• Towards Spontaneous Speech Translation

  1994cited by this paper
• JANUS 93: towards spontaneous speech translation

  1994cited by this paper
• The Meta-Pi Network: Building Distributed Knowledge Representations for Robust Multisource Pattern Recognition

  1992cited by this paper

• Articulatory Feature Classification Using Convolutional Neural Networks

  2018cites this paper
• Multilingual Modulation by Neural Language Codes

  2018cites this paper