paper-with-me

홈 › Papers

CMU’s IWSLT 2022 Dialect Speech Translation System

2022-05-01 · IWSLT (ACL) 2022 5 · Brian Yan, Patrick Fernandes, Siddharth Dalmia, Jiatong Shi, Yifan Peng, Dan Berrebbi, Xinyi Wang, Graham Neubig, Shinji Watanabe

This paper describes CMU’s submissions to the IWSLT 2022 dialect speech translation (ST) shared task for translating Tunisian-Arabic speech to English text. We use additional paired Modern Standard Arabic data (MSA) to directly improve the speech recognition (ASR) and machine translation (MT) components of our cascaded systems. We also augment the paired ASR data with pseudo translations via sequence-level knowledge distillation from an MT model and use these artificial triplet ST data to improve our end-to-end (E2E) systems. Our E2E models are based on the Multi-Decoder architecture with searchable hidden intermediates. We extend the Multi-Decoder by orienting the speech encoder towards the target language by applying ST supervision as hierarchical connectionist temporal classification (CTC) multi-task. During inference, we apply joint decoding of the ST CTC and ST autoregressive decoder branches of our modified Multi-Decoder. Finally, we apply ROVER voting, posterior combination, and minimum bayes-risk decoding with combined N-best lists to ensemble our various cascaded and E2E systems. Our best systems reached 20.8 and 19.5 BLEU on test2 (blind) and test1 respectively. Without any additional MSA data, we reached 20.4 and 19.2 on the same test sets.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderKnowledge DistillationMachine Translationspeech-recognitionSpeech RecognitionTranslationTriplet

Similar Papers 제목 키워드 기반

JHU IWSLT 2022 Dialect Speech Translation System Description

2022-05-01 · IWSLT (ACL) 2022 5 · Jinyi Yang, Amir Hussein, Matthew Wiesner, Sanjeev Khudanpur

This paper details the Johns Hopkins speech translation (ST) system used in the IWLST2022 dialect speech translation task. Our system uses a cascade of automatic speech recognition (ASR) and machine translation (MT). We …

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Machine Translationspeech-recognition+3

Findings of the IWSLT 2024 Evaluation Campaign

2024-11-07 · Ibrahim Said Ahmad, Antonios Anastasopoulos, Ondřej Bojar, Claudia Borg 외

This paper reports on the shared tasks organized by the 21st IWSLT Conference. The shared tasks address 7 scientific challenges in spoken language translation: simultaneous and offline translation, automatic subtitling a…

Speech-to-Speech TranslationTranslation

ON-TRAC Consortium Systems for the IWSLT 2022 Dialect and Low-resource Speech Translation Tasks

2022-05-04 · IWSLT (ACL) 2022 5 · Marcely Zanon Boito, John Ortega, Hugo Riguidel, Antoine Laurent 외

This paper describes the ON-TRAC Consortium translation systems developed for two challenge tracks featured in the Evaluation Campaign of IWSLT 2022: low-resource and dialect speech translation. For the Tunisian Arabic-E…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Machine Translationspeech-recognition+3

Findings of the IWSLT 2022 Evaluation Campaign

2022-05-01 · IWSLT (ACL) 2022 5 · Antonios Anastasopoulos, Loïc Barrault, Luisa Bentivogli, Marcely Zanon Boito 외

The evaluation campaign of the 19th International Conference on Spoken Language Translation featured eight shared tasks: (i) Simultaneous speech translation, (ii) Offline speech translation, (iii) Speech to speech transl…

Speech-to-Speech TranslationTranslation

The USTC-NEL Speech Translation system at IWSLT 2018

2018-12-06 · IWSLT (EMNLP) 2018 10 · Dan Liu, Junhua Liu, Wu Guo, Shifu Xiong 외

This paper describes the USTC-NEL system to the speech translation task of the IWSLT Evaluation 2018. The system is a conventional pipeline system which contains 3 modules: speech recognition, post-processing and machine…

Machine Translationspeech-recognitionSpeech RecognitionTranslation