Interactive voice technology at work: The CSELT experience

Billi, R.; Canavesio, F.; Ciaramella, Alberto; Nebbia, L.

doi:10.1016/0167-6393(95)00030-r

Cited by 6 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Apart from synthesizing English, in 1975 MUSA was a specialized software with the ability to read Italian. A second version, released in 1978, was also able to sing Italian in an "a cappella" style [4]. There had been still no multilingual TTS system until the year of 1997, when Bell labs published their research on synthesizing multi-languages [5], which extensively used natural language processing approach.…”

Section: Introductionmentioning

confidence: 99%

Development of Vietnamese Speech Synthesis System using Deep Neural Networks

Nguyen¹,

Nguyen²,

Phan³

et al. 2019

JCC

View full text Add to dashboard Cite

In this paper, we present our first Vietnamese speech synthesis system based on deep neural networks. To improve the training data collected from the Internet, a cleaning method is proposed. The experimental results indicate that by using deeper architectures we can achieve better performance for the TTS than using shallow architectures such as hidden Markov model. We also present the effect of using different amounts of data to train the TTS systems. In the VLSP TTS challenge 2018, our proposed DNN-based speech synthesis system won the first place in all three subjects including naturalness, intelligibility, and MOS.

show abstract

Section: Introductionmentioning

confidence: 99%

Development of Vietnamese Speech Synthesis System using Deep Neural Networks

Nguyen¹,

Nguyen²,

Phan³

et al. 2019

JCC

View full text Add to dashboard Cite

show abstract

“…The service delivers the name and address corresponding to a given phone number [6]. Input of the area code and telephone number is by pulse dialling or DTMF, output of the customer name and address by 'ITS (CSELT-ELOQUENS 2000).…”

Section: Reverse Directovy Service (Telecom Italia)mentioning

confidence: 99%

Current and experimental applications of speech technology for telecom services in Europe

Sorin¹,

Gagnoulet²,

Charpentier³

et al.

Proceedings of IVTTA '96. Workshop on Interactive Voice Technology for Telecommunications Applications

Self Cite

View full text Add to dashboard Cite

This paper provides an overview of oper&onal and experimental telephone services exploiting automatic speech recognition and/or text-to-speech in France, VK, Italy, Germany, Spain and Portugal. It illustrates a number of contemporary European systems and summarises the current status of a European project (EURESCOM P502 : MIVA, "Multilingual Interactive Voice Activated telephone services") which involves the Telecommunication Laboratories of these countries.technology. Monolingual laboratory tests are planned for October 1996 and multilingual field trials for March 97.Another goal of this project is to measure the impact of the different networks on the ASR performances, i.e. the potential performance degradation observed when building vocabulary models from recordings made for a given language on a given national telephone network and using them for recognition on another national network. This analysis should allow, in particular, to estimate the feasibility of sharing the vocabulary development costs for multilingual telephone services. FRANCE

show abstract