T5G2P: Using Text-to-Text Transfer Transformer for Grapheme-to-Phoneme Conversion
| dc.contributor.author | Řezáčková, Markéta | |
| dc.contributor.author | Švec, Jan | |
| dc.contributor.author | Tihelka, Daniel | |
| dc.date.accessioned | 2022-03-28T10:00:27Z | |
| dc.date.available | 2022-03-28T10:00:27Z | |
| dc.date.issued | 2021 | |
| dc.description.abstract-translated | Despite the increasing popularity of end-to-end text-to-speech (TTS) systems, the correct grapheme-to-phoneme (G2P) module is still a crucial part of those relying on a phonetic input. In this paper, we, therefore, introduce a T5G2P model, a Text-to-Text Transfer Transformer (T5) neural network model which is able to convert an input text sentence into a phoneme sequence with a high accuracy. The evaluation of our trained T5 model is carried out on English and Czech, since there are different specific properties of G2P, including homograph disambiguation, cross-word assimilation and irregular pronunciation of loanwords. The paper also contains an analysis of a homographs issue in English and offers another approach to Czech phonetic transcription using the detection of pronunciation exceptions. | en |
| dc.format | 5 s. | cs |
| dc.format.mimetype | application/pdf | |
| dc.identifier.citation | ŘEZÁČKOVÁ, M. ŠVEC, J. TIHELKA, D. T5G2P: Using Text-to-Text Transfer Transformer for Grapheme-to-Phoneme Conversion. In Proceedings of the Annual Conference of the International Speech Communication Association, Interspeech. Red Hook, NY: International Speech Communication Association, 2021. s. 3291-3295. ISBN: 978-1-71383-690-2 , ISSN: 2308-457X | cs |
| dc.identifier.doi | 10.21437/Interspeech.2021-546 | |
| dc.identifier.isbn | 978-1-71383-690-2 | |
| dc.identifier.issn | 2308-457X | |
| dc.identifier.obd | 43933414 | |
| dc.identifier.uri | 2-s2.0-85115262876 | |
| dc.identifier.uri | http://hdl.handle.net/11025/47249 | |
| dc.language.iso | en | en |
| dc.project.ID | GA19-19324S/Plně trénovatelná syntéza české řeči z textu s využitím hlubokých neuronových sítí | cs |
| dc.project.ID | SGS-2019-027/Inteligentní metody strojového vnímání a porozumění 4 | cs |
| dc.project.ID | 90140/Velká výzkumná infrastruktura_(J) - e-INFRA CZ | cs |
| dc.publisher | International Speech Communication Association | en |
| dc.relation.ispartofseries | Proceedings of the Annual Conference of the International Speech Communication Association, Interspeech | en |
| dc.rights | Plný text není přístupný. | cs |
| dc.rights | © ISCA | en |
| dc.rights.access | closedAccess | en |
| dc.subject.translated | grapheme-to-phoneme | en |
| dc.subject.translated | phonetic transcription | en |
| dc.subject.translated | T5 | en |
| dc.subject.translated | transformers | en |
| dc.subject.translated | TTS system | en |
| dc.title | T5G2P: Using Text-to-Text Transfer Transformer for Grapheme-to-Phoneme Conversion | en |
| dc.type | konferenční příspěvek | cs |
| dc.type | ConferenceObject | en |
| dc.type.status | Peer-reviewed | en |
| dc.type.version | publishedVersion | en |
Files
Original bundle
1 - 1 out of 1 results
No Thumbnail Available
- Name:
- rezackova21_interspeech.pdf
- Size:
- 167.67 KB
- Format:
- Adobe Portable Document Format