Spanish to english speech to text7/23/2023 ![]() We present the first system for this problem applied to a realistic multi-speaker dataset, the CALLHOME Spanish-English speech translation corpus. ![]() Publisher = "Association for Computational Linguistics",Ībstract = "We explore the problem of translating speech to text in low-resource scenarios where neither automatic speech recognition (ASR) nor machine translation (MT) are available, but we have training data in the form of audio paired with text translations. Cite (Informal): Towards speech-to-text translation without speech recognition (Bansal et al., EACL 2017) Copy Citation: BibTeX Markdown MODS XML Endnote More options… PDF: = "Towards speech-to-text translation without speech recognition",īooktitle = "Proceedings of the 15th Conference of the uropean Chapter of the Association for Computational Linguistics: Volume 2, Short Papers", Association for Computational Linguistics. ![]() In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 474–479, Valencia, Spain. Towards speech-to-text translation without speech recognition. Anthology ID: E17-2076 Volume: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers Month: April Year: 2017 Address: Valencia, Spain Venue: EACL SIG: Publisher: Association for Computational Linguistics Note: Pages: 474–479 Language: URL: DOI: Bibkey: bansal-etal-2017-towards Cite (ACL): Sameer Bansal, Herman Kamper, Adam Lopez, and Sharon Goldwater. We identify the challenges faced by the system, finding that the difficulty of cross-speaker UTD results in low recall, but that our system is still able to correctly translate some content words in test data. Our approach uses unsupervised term discovery (UTD) to cluster repeated patterns in the audio, creating a pseudotext, which we pair with translations to create a parallel text and train a simple bag-of-words MT model. Abstract We explore the problem of translating speech to text in low-resource scenarios where neither automatic speech recognition (ASR) nor machine translation (MT) are available, but we have training data in the form of audio paired with text translations.
0 Comments
Leave a Reply. |