paper-with-me

홈 › Papers

Effectively pretraining a speech translation decoder with Machine Translation data

2020-11-01 · EMNLP 2020 11 · Ashkan Alinejad, Anoop Sarkar

Directly translating from speech to text using an end-to-end approach is still challenging for many language pairs due to insufficient data. Although pretraining the encoder parameters using the Automatic Speech Recognition (ASR) task improves the results in low resource settings, attempting to use pretrained parameters from the Neural Machine Translation (NMT) task has been largely unsuccessful in previous works. In this paper, we will show that by using an adversarial regularizer, we can bring the encoder representations of the ASR and NMT tasks closer even though they are in different modalities, and how this helps us effectively use a pretrained NMT decoder for speech translation.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DecoderMachine TranslationNMTspeech-recognitionSpeech RecognitionSpeech-to-TextTranslation

Similar Papers 제목 키워드 기반

Unveiling the Role of Pretraining in Direct Speech Translation

2024-09-26 · Belen Alastruey, Gerard I. Gállego, Marta R. Costa-jussà

Direct speech-to-text translation systems encounter an important drawback in data scarcity. A common solution consists on pretraining the encoder on automatic speech recognition, hence losing efficiency in the training p…

Automatic Speech RecognitionDecoderspeech-recognitionSpeech Recognition+3

Start-Before-End and End-to-End: Neural Speech Translation by AppTek and RWTH Aachen University

2020-07-01 · WS 2020 7 · Parnia Bahar, Patrick Wilken, Tamer Alkhouli, Andreas Guta 외

AppTek and RWTH Aachen University team together to participate in the offline and simultaneous speech translation tracks of IWSLT 2020. For the offline task, we create both cascaded and end-to-end speech translation syst…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DecoderMachine Translation+4

Compact Speech Translation Models via Discrete Speech Units Pretraining

2024-02-29 · Tsz Kin Lam, Alexandra Birch, Barry Haddow

We propose a pretraining method to use Self-Supervised Speech (SSS) model to creating more compact Speech-to-text Translation. In contrast to using the SSS model for initialization, our method is more suitable to memory …

DecoderSelf-Supervised LearningSpeech-to-TextSpeech-to-Text Translation+1

Revisiting End-to-End Speech-to-Text Translation From Scratch

2022-06-09 · Biao Zhang, Barry Haddow, Rico Sennrich

End-to-end (E2E) speech-to-text translation (ST) often depends on pretraining its encoder and/or decoder using source transcripts via speech recognition or text translation tasks, without which translation performance dr…

Decoderspeech-recognitionSpeech RecognitionSpeech-to-Text+2

Pretraining by Backtranslation for End-to-end ASR in Low-Resource Settings

2018-12-10 · Matthew Wiesner, Adithya Renduchintala, Shinji Watanabe, Chunxi Liu 외

We explore training attention-based encoder-decoder ASR in low-resource settings. These models perform poorly when trained on small amounts of transcribed speech, in part because they depend on having sufficient target-s…

Data AugmentationDecoder