paper-with-me

Papers

Cascaded Models With Cyclic Feedback For Direct Speech Translation

2020-10-21 · Tsz Kin Lam, Shigehiko Schamoni, Stefan Riezler

Direct speech translation describes a scenario where only speech inputs and corresponding translations are available. Such data are notoriously limited. We present a technique that allows cascades of automatic speech recognition (ASR) and machine translation (MT) to exploit in-domain direct speech translation data in addition to out-of-domain MT and ASR data. After pre-training MT and ASR, we use a feedback cycle where the downstream performance of the MT system is used as a signal to improve the ASR system by self-training, and the MT component is fine-tuned on multiple ASR outputs, making it more tolerant towards spelling variations. A comparison to end-to-end speech translation using components of identical architecture and the same data shows gains of up to 3.8 BLEU points on LibriVoxDeEn and up to 5.1 BLEU points on CoVoST for German-to-English speech translation.

📄 PDF Abstract BibTeX arXiv:2010.11153

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Machine Translationspeech-recognitionSpeech RecognitionTranslation

Similar Papers 제목 키워드 기반

ZJU’s IWSLT 2021 Speech Translation System

2021-08-01 · ACL (IWSLT) 2021 8 · Linlin Zhang

In this paper, we describe Zhejiang University’s submission to the IWSLT2021 Multilingual Speech Translation Task. This task focuses on speech translation (ST) research across many non-English source languages. Participa…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Machine TranslationNMT+3

Does Joint Training Really Help Cascaded Speech Translation?

2022-10-24 · Viet Anh Khoa Tran, David Thulke, Yingbo Gao, Christian Herold 외

Currently, in speech translation, the straightforward approach - cascading a recognition system with a translation system - delivers state-of-the-art results. However, fundamental challenges such as error propagation fro…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition+1

Direct Simultaneous Speech-to-Speech Translation with Variational Monotonic Multihead Attention

2021-10-15 · Xutai Ma, Hongyu Gong, Danni Liu, Ann Lee 외

We present a direct simultaneous speech-to-speech translation (Simul-S2ST) model, Furthermore, the generation of translation is independent from intermediate text representations. Our approach leverages recent progress o…

Simultaneous Speech-to-Speech TranslationSpeech SynthesisSpeech-to-Speech TranslationTranslation

Improving Cascaded Unsupervised Speech Translation with Denoising Back-translation

2023-05-12 · Yu-Kuan Fu, Liang-Hsuan Tseng, Jiatong Shi, Chen-An Li 외

Most of the speech translation models heavily rely on parallel data, which is hard to collect especially for low-resource languages. To tackle this issue, we propose to build a cascaded speech translation system without …

DenoisingMachine TranslationTranslation

SpeechQE: Estimating the Quality of Direct Speech Translation

2024-10-28 · Hyojung Han, Kevin Duh, Marine Carpuat

Recent advances in automatic quality estimation for machine translation have exclusively focused on written language, leaving the speech modality underexplored. In this work, we formulate the task of quality estimation f…

Machine TranslationTranslation