Machine generated speech can be produced in different ways however there are two basic methods for synthesizing speech in widespread use. One method generates speech from models, while the other method concatenates pre-stored speech segments. This paper presents a speech synthesis technique where these two basic synthesis methods are combined in a statistical framework. Synthetic speech is cons...

The primary objective of this paper is to provide an overview of existing Concatenative Text-To-Speech synthesis techniques. Concatenative speech synthesis can be broadly categorized into three categories, Diphone Based, Corpus based and Hybrid. Diphone based speech synthesis relies on different signal processing techniques such as PSOLA, FD-PSOLA etc. These signal processing techniques introdu...

Articulatory speech synthesis models the natural speech production process. As a speech synthesis method it is not among the best, when the quality of produced speech sounds is the main criterion. However, for studying speech production it is the most suitable method. This thesis reviews the literature on articulatory speech synthesis. The objective is to look at articulatory speech synthesis f...

This paper proposes a new concatenative speech synthesis method using context dependent phoneme sequences with variable length as search units. Using Japanese broadcast news programs as a speech database, we synthesize Japanese news sentences that are not included in that speech database and perform subjective evaluations of the synthesized speech. As a result, (1) 77% of speech synthesized by ...

In this paper, we propose a non-realtime speech bandwidth extension method using HMM-based speech recognition and HMM-based speech synthesis. In the proposed method, first, the phoneme-state sequence is estimated from the bandlimited speech signals using the speech recognition technique. Next, for estimating spectrum envelopes of lost high-frequency components, an HMM-based speech synthesis tec...

Concatenative speech synthesis is a method that can make speech sound which has naturalness and high-individuality of a speaker by introducing a large speech corpus. Based on this method, in this paper, we propose a voice conversion method whose conversion speech has high-individuality and naturalness. The authors also have two subjective evaluation experiments for evaluating individuality and ...

This paper proposes a new speech synthesis method for high-quality Japanese TTS(Text-to-speech) based on the waveform synthesis. The method uses V-CV as a basic synthesis unit to preserve the intelligibility of consonant. An efficient unit reconstruction method is newly adopted both to minimize pitch conversion and concatenation distortion when selecting waveforms. The minimization can provide ...

As described in this paper, we propose a sub-band speech synthesis approach to develop a high quality Text-to-Speech (TTS) system: a sample-based spectrum is used in the high-frequency band and spectrum generated by HMM-based TTS is used in the low-frequency band. Herein, sample-based spectrum means spectrum selected from a phoneme database such that it is the most similar to spectrum generated...

Current developments in artificial speech synthesis place more emphasis on spectral continuities and diverse prosodic effects. The trainable HMM-based speech synthesis method has generated more continuous spectral structure than unit selection method in recent study, but the pitch contour generated by HMM-based method trends to be over-smoothed and lacks syllable variance in Chinese. In this pa...

People and things can be connected through the Internet of Things (IoT), speech synthesis is one key technologies. At this stage, end-to-end systems are capable synthesizing relatively realistic human voices, but current commonly used parallel text-to-speech suffers from loss useful information during two-stage delivery process, control features synthesized monotonous, with insufficient express...