Current State of Text-to-Speech System ARTIC: A Decade of Research on the Field of Speech Technologies

GMM-Based Evaluation of Synthetic Speech Quality Using 2D Classification in Pleasure-Arousal Scale

“…Considering the limitation of the current work and its potential for practical use by other researchers we plan to build larger speech corpora and perform next evaluation experiments with the aim to find any fusion method how to enable comparison with the results obtained from the evaluation of the listening test. The Czech TTS system tested is also able to produce synthetic speech in the Slovak language (similar to Czech) [16,31]; therefore, we also suppose the application of Slovak in this proposed automatic evaluation system. Finally, we will attempt to collect speech databases directly in the Czech (Slovak) languages with sentences labeled on the P-A scale for the subsequent creation of GMM models used in the continuous P-A classification.…”

“…To evaluate synthetic speech quality by continual classification in the P-A scale, we collected the first speech corpus (SC1) consisting of three parts: the original speech uttered by real speakers, and two variations of speech synthesis produced by the Czech TTS system using the USEL method [16] with voices based on the original speaker. Two methods of prosody manipulation were applied: the rule-based method (assigned as TTS A ) and the modified version reflecting the final syllable status (as TTS B ) [11].…”

“…The second collected speech corpus (SC2) consists of four parts: the natural speech uttered by the original speakers and three variations of speech synthesis: the USEL based TTS system (assigned to Synt1) and two LSTM based systems with different vocoders: conventional WORLD (further referred to as Synt2) [16], WaveRNN (referred to as Synt3) [17]. As in the case of SC1, the original and synthetic speech originated from the speakers M1, M2, and F1, F2.…”

“…In the second basic evaluation experiment, the three tested types of speech synthesis were the following: (1) the basic USEL synthesis, (2) the synthesis using a deep neural network (DNN) with a long short-term memory (LSTM) and a conventional WORLD vocoder [16], (3) the synthesis using a recurrent neural network with the LSTM and a WaveRNN [17] vocoder. The speech synthesized by the methods using the neural networks is typologically different from that produced by the USEL synthesizer.…”

Unified Language-Independent DNN-Based G2P Converter

“…Our current G2P converter was originally designed nearly 20 years ago within a development of our new text-to-speech (TTS) system ARTIC [18] to primarily handle the Czech language, but other languages like Slovak [19,20], Russian, English and Armenian were added as well during this period [21]. It is based on the combination of rules and simple key-value dictionary, where the dictionary is searched first (to handle pronunciation irregularities not covered or coverable by rules), and when no appropriate key is found, the rules are applied.…”