%Aigaion2 BibTeX export from Idiap Publications %Saturday 21 December 2024 06:12:50 PM @TECHREPORT{Goldman_Idiap-RR-13-2016, author = {Goldman, Jean-Philippe and Honnet, Pierre-Edouard and Clark, Rob and Garner, Philip N. and Ivanova, Maria and Lazaridis, Alexandros and Liang, Hui and Macedo, Tiago and Pfister, Beat and Ribeiro, Manuel Sam and Wehrli, Eric and Yamagishi, Junichi}, keywords = {bilingual speakers, emphasis, speech corpus, speech-to-speech translation}, projects = {Idiap, SIWIS}, month = {5}, title = {The SIWIS database: a multilingual speech database with acted emphasis}, type = {Idiap-RR}, number = {Idiap-RR-13-2016}, year = {2016}, institution = {Idiap}, abstract = {We describe here a collection of speech data of bilingual and trilingual speakers of English, French, German and Italian. In the context of speech to speech translation (S2ST), this database is designed for several purposes and studies: training CLSA systems (cross-language speaker adaptation), conveying emphasis through S2ST systems, and evaluating TTS systems. More precisely, 36 speakers judged as accentless (22 bilingual and 14 trilingual speakers) were recorded for a set of 171 prompts in two or three languages, amounting to a total of 24 hours of speech. These sets of prompts include 100 sentences from news, 25 sentences from Europarl, the same 25 sentences with one acted emphasised word, 20 semantically unpredictable sentences, and finally a 240-word long text. All in all, it yielded 64 bilingual session pairs of the six possible combinations of the four languages. The database is freely available for non-commercial use and scientific research purposes.}, pdf = {https://publications.idiap.ch/attachments/reports/2016/Goldman_Idiap-RR-13-2016.pdf} }