Abstract
Recently, we have seen an increasing interest in the area of speech-to-text translation. This has led to astonishing improvements in this area. In contrast, the activities in the area of speech-to-speech translation is still limited, although it is essential to overcome the language barrier. We believe that one of the limiting factors is the availability of appropriate training data. We address this issue by creating LibriS2S, to our knowledge the first publicly available speech-to-speech training corpus between German and English.For this corpus, we used independently created audio for German and English leading to an unbiased pronunciation of the text in both languages. This allows the creation of a new text-to-speech and speech-to-speech translation model that directly learns to generate the speech signal based on the pronunciation of the source language.Using this created corpus, we propose Text-to-Speech models based on the example of the recently proposed FastSpeech 2 model that integrates source language information. We do this by adapting the model to take information such as the pitch, energy or transcript from the source speech as additional input.
Original language | English |
---|---|
Title of host publication | Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022) |
Publisher | European Language Resources Association |
Pages | 928-935 |
Number of pages | 8 |
ISBN (Print) | 9791095546726 |
Publication status | Published - 2022 |
Event | 13th International Conference on Language Resources and Evaluation (LREC) - Le Palais du Pharo, Marseille, France Duration: 20 Jun 2022 → 25 Jun 2022 https://lrec2022.lrec-conf.org/en/ |
Conference
Conference | 13th International Conference on Language Resources and Evaluation (LREC) |
---|---|
Abbreviated title | LREC 2022 |
Country/Territory | France |
City | Marseille |
Period | 20/06/22 → 25/06/22 |
Internet address |
Keywords
- Speech-to-Speech translation
- Speech synthesis
- Dataset creation