Building LSTM neural network based speaker identification system

Laurynas Dovydaitis, Vytautas Rudžionis

Abstract


In this paper, we are analyzing the results of native Lithuanian speaker recognition and identification using long short-term memory deep neural network. We look at recognition accuracy and identify further potential improvements. Dataset used for training and speaker recognition consists of over 370 unique speakers, who provide their voice utterances in Lithuanian language. In this paper we present results that are derived from part of this dataset.

DOI: 10.15181/csat.v6i1.1579


References


Abdallah, S. J., Osman, I. M., Mustafa, M. E., Text-Independent Speaker Identification Using Hidden Markov Model, 2012, World of Computer Science and Information Technology Journal (WCSIT) ISSN: 2221-0741 Vol. 2, No. 6

Bhattacharya, G., Alam, J., Stafylakis, T., Kenny, P., Deep Neural Network based Text-Dependent Speaker Recognition: Preliminary Results, Odyssey 2016, June 21-24, 2016, Bilbao, Spain

Deshmukh S.D., Bachute M.R., Automatic Speech and Speaker Recognition by MFCC, HMM and Vector Quantization, International Journal of Engineering and Innovative Technology (IJEIT) Volume 3, Issue 1, July 2013

Fakotakis, N., Georgila, K., Tsopanoglou, A., A Countinous HMM text-independent sepeaker recognition systems based on viwel spotting, 1997, EUROSPEECH'97, 5th European Conference on Speech Communication and Technology

Graves A., Schmidhuber J., Framewise phoneme classification with bidirectional LSTM and other neural network architectures, 2005, Neural Networks, Volume 18, Issues 5–6, July–August 2005, Pages 602-610

Laurinčiukaitė, S., Telksnys, L., Kasparaitis, P., Kliukienė, R., Paukštytė, V., Lithuanian Speech Corpus Liepa for the Development of Lithuanian Speech Controlled Equipment, Submitted to journal INFORMATICA, Vilnius University, 2017

Mahola, U., Nelwamondo F. V., Marwala, T., HMM Speaker Identification Using Linear and Non-linear Merging Techniques, 2007, arXiv:0705.1585

Ringelienė, Ž., Filipovič, M., Žodžių atpažinimo, grįsto paslėptaisiais Markovo modeliais, vizualizavimo ir analizės programinė įranga, INFORMACIJOS MOKSLAI. 2011 56, ISSN 1392-0561

The Hidden Markov Model Toolkit (HTK), prieiga per internetą http://htk.eng.cam.ac.uk/, paskutinį kartą kreiptasi 2017/05/02

Tiwari, V.: MFCC and its applications in speaker recognition. International Journal on Emerging Technologies 1(1), 19-22(2010)


Full Text: PDF

Refbacks

  • There are currently no refbacks.

Comments on this article

View all comments


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.

eISSN: 2029-9966

Creative Commons License