paper-with-me

Papers

Unified Speech-Text Pre-training for Speech Translation and Recognition

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

In this work, we describe a method to jointly pre-train speech and text in an encoder-decoder modeling framework for speech translation and recognition. The proposed method utilizes multi-task learning to integrate four self-supervised and supervised subtasks for cross modality learning. A self-supervised speech subtask, which leverages unlabelled speech data, and a (self-)supervised text to text subtask, which makes use of abundant text training data, take up the majority of the pre-training time. Two auxiliary supervised speech tasks are included to unify speech and text modeling space. Detailed analysis reveals learning interference among subtasks. In order to alleviate the subtask interference, two pre-training configurations are proposed for speech translation and speech recognition respectively. Our experiments show the proposed method can effectively fuse speech and text information into one model. It achieves between 1.7 and 2.3 BLEU improvement above the state of the art on the MuST-C speech translation dataset and comparable WERs to wav2vec 2.0 on the Librispeech speech recognition task.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderMulti-Task Learningspeech-recognitionSpeech RecognitionTranslation

Similar Papers 제목 키워드 기반

Fused Acoustic and Text Encoding for Multimodal Bilingual Pretraining and Speech Translation

2021-02-10 · Renjie Zheng, Junkun Chen, Mingbo Ma, Liang Huang

Recently, representation learning for text and speech has successfully improved many language related tasks. However, all existing methods suffer from two limitations: (a) they only learn from one input modality, while a…

Language ModelingLanguage ModellingMachine TranslationRepresentation Learning+3

Unified Speech-Text Pre-training for Speech Translation and Recognition

2022-04-11 · ACL 2022 5 · Yun Tang, Hongyu Gong, Ning Dong, Changhan Wang 외

We describe a method to jointly pre-train speech and text in an encoder-decoder modeling framework for speech translation and recognition. The proposed method incorporates four self-supervised and supervised subtasks for…

Decoderspeech-recognitionSpeech RecognitionTranslation

SeamlessM4T: Massively Multilingual & Multimodal Machine Translation

2023-08-22 · Seamless Communication, Loïc Barrault, Yu-An Chung, Mariano Cora Meglioli 외

What does it take to create the Babel Fish, a tool that can help individuals translate speech between any two languages? While recent breakthroughs in text-based models have pushed machine translation coverage beyond 200…

Automatic Speech RecognitionMachine TranslationSpeech-to-Speech TranslationSpeech-to-Text+5

Multilingual Speech Translation with Unified Transformer: Huawei Noah’s Ark Lab at IWSLT 2021

2021-08-01 · ACL (IWSLT) 2021 8 · Xingshan Zeng, Liangyou Li, Qun Liu

This paper describes the system submitted to the IWSLT 2021 Multilingual Speech Translation (MultiST) task from Huawei Noah’s Ark Lab. We use a unified transformer architecture for our MultiST model, so that the data fro…

Data AugmentationDecoderMachine TranslationMulti-Task Learning+3

Multilingual Speech Translation with Unified Transformer: Huawei Noah's Ark Lab at IWSLT 2021

2021-06-01 · Xingshan Zeng, Liangyou Li, Qun Liu

This paper describes the system submitted to the IWSLT 2021 Multilingual Speech Translation (MultiST) task from Huawei Noah's Ark Lab. We use a unified transformer architecture for our MultiST model, so that the data fro…

Data AugmentationDecoderMachine TranslationMulti-Task Learning+3