Speech synthesis models: a review

Breen, Andrew P.

doi:10.1049/ecej:19920006

Cited by 14 publications

(7 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…After performing glitch removal on the sequence of speech feature indices, a concatenation synthesis method [26] is applied to reconstruct the target speech in a frame-by-frame basis. Based on the speech feature indices, target phoneme frames are loaded from the pre-recorded set and concatenated to form the complete speech.…”

Section: Speech Synthesis and Glitch Removalmentioning

confidence: 99%

Non-acoustic Communication with Speech Smoothing

Lam¹

2012

SIPIJ

View full text Add to dashboard Cite

Section: Speech Synthesis and Glitch Removalmentioning

confidence: 99%

Non-acoustic Communication with Speech Smoothing

Lam¹

2012

SIPIJ

View full text Add to dashboard Cite

“…As the technology advances, the number of applications will increase. However, many of them are awaiting the time when text-to-speech system can produce natural sounding speech [1].…”

Section: Introductionmentioning

confidence: 99%

Design of co-processor for real-time HMM-based text-to-speech on hardware system applied to Vietnamese

Hoang

Nguyen

et al. 2015

IEICE Electron. Express

View full text Add to dashboard Cite

Although HMM-based TTS has been studied for many years, there are some limitations such as real-time applications based on lowperformance and low cost systems. In this paper, we present a design of a TTS co-processor used for HMM-based Text-to-Speech (TTS) hardware systems. Based on a dedicated FPU and resource sharing architecture, the coprocessor can compute a lot of DSP algorithms required by HMM at very high speed. The system has been built and verified on the FPGA system with English and Vietnamese languages. The results show that it can compute up to 3 words per second at frequency of 100 MHz with the resources cost about 32,000 logic elements, 19,000 registers, and 957 KB memory.

show abstract

“…been review recently by Breen (1992). Basically, the synThe first is by smoothing as in the cases of FIGS.…”

mentioning

confidence: 99%