@inproceedings{6edf5873723c46e2be6887060bf82c6c,
title = "On development deep neural network speech synthesis using vector quantized acoustical feature for isolated bahasa Indonesia words",
abstract = "Speech representation and transformation using adaptive interpolation of weighted spectrum (STRAIGHT) is well known as high quality vocoder-and-synthesizer method for both voice recognition and speech synthesis. Especially on speech synthesis, choosing STRAIGHT is reasonable scheme to produce good speech sound. A problem appears when relating linguistic feature and STRAIGHT with high dimensional acoustical feature that is modelled by the neural network. The computational cost rises too high and becomes inefficient to be used as neural network output feature. VQ approximates aperiodicity and smoothed spectrum parameter on to a numbers of centroid vectors. This paper examines scenario to reduce the computational cost yet the quality remains good using vector quantization (VQ) method. Experimental results show that VQ based Speech Synthesis produce nearly inaudible distortion with DMOS at about 3.82 on the synthesized speech.",
keywords = "bahasa, deep neural network, speech synthesis, vector quantization",
author = "Manunggal, {Trikarsa Tirtadwipa} and Dhany Arifianto",
note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 19th Annual Conference of the Oriental Chapter of International Committee for Coordination and Standardization of Speech Databases and Assessment Techniques, O-COCOSDA 2016 ; Conference date: 26-10-2016 Through 28-10-2016",
year = "2017",
month = may,
day = "3",
doi = "10.1109/ICSDA.2016.7918993",
language = "English",
series = "2016 Conference of the Oriental Chapter of International Committee for Coordination and Standardization of Speech Databases and Assessment Techniques, O-COCOSDA 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "105--109",
booktitle = "2016 Conference of the Oriental Chapter of International Committee for Coordination and Standardization of Speech Databases and Assessment Techniques, O-COCOSDA 2016",
address = "United States",
}