paper-with-me

홈 › Papers

Improving Speech-to-Speech Translation Through Unlabeled Text

2022-10-26 · Xuan-Phi Nguyen, Sravya Popuri, Changhan Wang, Yun Tang, Ilia Kulikov, Hongyu Gong

Direct speech-to-speech translation (S2ST) is among the most challenging problems in the translation paradigm due to the significant scarcity of S2ST data. While effort has been made to increase the data size from unlabeled speech by cascading pretrained speech recognition (ASR), machine translation (MT) and text-to-speech (TTS) models; unlabeled text has remained relatively under-utilized to improve S2ST. We propose an effective way to utilize the massive existing unlabeled text from different languages to create a large amount of S2ST data to improve S2ST performance by applying various acoustic effects to the generated synthetic data. Empirically our method outperforms the state of the art in Spanish-English translation by up to 2 BLEU. Significant gains by the proposed method are demonstrated in extremely low-resource settings for both Spanish-English and Russian-English translations.

📄 PDF Abstract BibTeX arXiv:2210.14514

Code (0)

등록된 구현이 없습니다.

Tasks

Machine Translationspeech-recognitionSpeech RecognitionSpeech-to-Speech Translationtext-to-speechText to SpeechTranslation

Similar Papers 제목 키워드 기반

Mu$^{2}$SLAM: Multitask, Multilingual Speech and Language Models

2022-12-19 · Yong Cheng, Yu Zhang, Melvin Johnson, Wolfgang Macherey 외

We present Mu$^{2}$SLAM, a multilingual sequence-to-sequence model pre-trained jointly on unlabeled speech, unlabeled text and supervised data spanning Automatic Speech Recognition (ASR), Automatic Speech Translation (AS…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)automatic-speech-translationDecoder+8

Improving End-to-end Speech Translation by Leveraging Auxiliary Speech and Text Data

2021-11-16 · ACL ARR November 2021 11 · Anonymous

We present a method for introducing a text encoder into pre-training end-to-end speech translation systems. It enhances the ability of adapting one modality (i.e., source-language speech) to another (i.e., source-languag…

de-enDenoisingTranslation

Improving End-to-end Speech Translation by Leveraging Auxiliary Speech and Text Data

2022-12-04 · Yuhao Zhang, Chen Xu, Bojie Hu, Chunliang Zhang 외

We present a method for introducing a text encoder into pre-trained end-to-end speech translation systems. It enhances the ability of adapting one modality (i.e., source-language speech) to another (i.e., source-language…

de-enDenoisingTranslation

SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training

2021-10-20 · Ankur Bapna, Yu-An Chung, Nan Wu, Anmol Gulati 외

Unsupervised pre-training is now the predominant approach for both text and speech understanding. Self-attention models pre-trained on large amounts of unannotated data have been hugely successful when fine-tuned on down…

Language ModelingLanguage ModellingText MatchingText Normalization+2

mSLAM: Massively multilingual joint pre-training for speech and text

2022-02-03 · Ankur Bapna, Colin Cherry, Yu Zhang, Ye Jia 외

We present mSLAM, a multilingual Speech and LAnguage Model that learns cross-lingual cross-modal representations of speech and text by pre-training jointly on large amounts of unlabeled speech and text in multiple langua…

cross-modal alignmentintent-classificationIntent ClassificationLanguage Modeling+4