paper-with-me

Papers

Segmentation-Free Streaming Machine Translation

2023-09-26 · Javier Iranzo-Sánchez, Jorge Iranzo-Sánchez, Adrià Giménez, Jorge Civera, Alfons Juan

Streaming Machine Translation (MT) is the task of translating an unbounded input text stream in real-time. The traditional cascade approach, which combines an Automatic Speech Recognition (ASR) and an MT system, relies on an intermediate segmentation step which splits the transcription stream into sentence-like units. However, the incorporation of a hard segmentation constrains the MT system and is a source of errors. This paper proposes a Segmentation-Free framework that enables the model to translate an unsegmented source stream by delaying the segmentation decision until the translation has been generated. Extensive experiments show how the proposed Segmentation-Free framework has better quality-latency trade-off than competing approaches that use an independent segmentation model. Software, data and models will be released upon paper acceptance.

📄 PDF Abstract BibTeX arXiv:2309.14823

Code (1)

jairsan/segmentation-free_streaming_machine_translation 공식 구현

Tasks

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

Similar Papers 제목 키워드 기반

Direct Segmentation Models for Streaming Speech Translation

2020-11-01 · EMNLP 2020 11 · Javier Iranzo-S{\'a}nchez, Adri{\`a} Gim{\'e}nez Pastor, Joan Albert Silvestre-Cerd{\`a}, Pau Baquero-Arnal 외

The cascade approach to Speech Translation (ST) is based on a pipeline that concatenates an Automatic Speech Recognition (ASR) system followed by a Machine Translation (MT) system. These systems are usually connected by …

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

Stream-level Latency Evaluation for Simultaneous Machine Translation

2021-04-18 · Findings (EMNLP) 2021 11 · Javier Iranzo-Sánchez, Jorge Civera, Alfons Juan

Simultaneous machine translation has recently gained traction thanks to significant quality improvements and the advent of streaming applications. Simultaneous translation systems need to find a trade-off between transla…

Machine TranslationSentenceTranslation

BIT's system for the AutoSimTrans 2020

2020-07-01 · WS 2020 7 · Minqin Li, Haodong Cheng, Yuanjie Wang, Sijia Zhang 외

This paper describes our machine translation systems for the streaming Chinese-to-English translation task of AutoSimTrans 2020. We present a sentence length based method and a sentence boundary detection model based met…

Boundary DetectionMachine TranslationSentenceTranslation

Streaming Translation and Transcription Through Speech-to-Text Causal Alignment

2026-03-12 · Roman Koshkin, Jeon Haesung, Lianbo Liu, Hao Shi 외 arxiv

Simultaneous machine translation (SiMT) has traditionally relied on offline machine translation models coupled with human-engineered heuristics or learned policies. We propose Hikari, a policy-free, fully end-to-end mode…

Speech-to-Text TranslationMachine Translation

End-to-End Simultaneous Speech Translation with Differentiable Segmentation

2023-05-25 · Shaolei Zhang, Yang Feng

End-to-end simultaneous speech translation (SimulST) outputs translation while receiving the streaming speech inputs (a.k.a. streaming speech translation), and hence needs to segment the speech inputs and then translate …

SegmentationTranslation