Improving Phonetic Recognition with Sequence-length Standardized MFCC Features and Deep Bi-Directional LSTM

Phonetic recognition is one of the most challenging problems in the field of speech analysis. These applications can be mentioned such as dialect identification [1], mispronunciation detection [2], spoken document retrieval [3], and so on. There are different approaches to solve these problems such as improving the feature selection on input speech [4], applying deep learning technique [5] [6] [7] or combining both of them [8]. With the sequence data as the phonetics, the architecture which is based on recurrent neural network (RNN) is an appropriate approach [9]. It is even more powerful when combined with the improvement of features selection on input data. In our approach, we combine the Mel Frequency Cepstral Coefficients (MFCC) method with sequence-length to present the acoustic features of speech and use some RNN models to phonetic classification. Our experiments are implemented on the Texas Instruments Massachusetts Institute of Technology (TIMIT) [10] phone recognition dataset. Especially, our data processing and features selection method give consistently better results than other researches using the same neural network model. Currently, we have achieved the lowest error test rate (13.05%) by using Bidirectional LSTM, which is the best result in TIMIT dataset with the reduction of about 3.5% over the last best result [5] [6].

• Publication year

  2018

• Venue

  National Foundation for Science and Technology Development Conference on Information and Computer Science

• Publication date

  2018-11-01

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.1109/NICS.2018.8606886
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Learning Filterbanks from Raw Speech for Phone Recognition

  2017cited by this paper
• A Regularization Post Layer: An Additional Way How to Make Deep Neural Networks Robust

  2017cited by this paper
• Segmental Recurrent Neural Networks for End-to-End Speech Recognition

  2016cited by this paper
• Weakly Supervised Memory Networks

  2015cited by this paper
• Attention-Based Models for Speech Recognition

  2015cited by this paper
• Phone recognition with hierarchical convolutional deep maxout networks

  2015cited by this paper
• Combining time- and frequency-domain convolution in convolutional neural network-based phone recognition

  2014cited by this paper
• Adam: A Method for Stochastic Optimization

  2014cited by this paper
• Speech recognition with deep recurrent neural networks

  2013cited by this paper
• Sequence Transduction with Recurrent Neural Networks

  2012cited by this paper
• Phoneme Recognition on the TIMIT Database

  2011cited by this paper
• Implementation of an extended recognition network for mispronunciation detection and diagnosis in computer-assisted pronunciation training

  2009cited by this paper
• Deep Belief Networks for phone recognition

  2009cited by this paper
• Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks

  2006cited by this paper
• Phonetic recognition for spoken document retrieval

  1998cited by this paper
• Transcription and Alignment of the TIMIT Database

  1996cited by this paper
• Automatic dialect identification of extemporaneous conversational, Latin American Spanish speech

  1996cited by this paper
• DARPA TIMIT:: acoustic-phonetic continuous speech corpus CD-ROM, NIST speech disc 1-1.1

  1993influential reference
• Speaker-independent phone recognition using hidden Markov models

  1989cited by this paper

• NS-SVM: Bolstering Chicken Egg Harvesting Prediction with Normalization and Standardization

  2023cites this paper