Translating On the Go? Investigating the Potential of Multimodal Mobile Devices for Interactive Translation Dictation

Zapata, Julián

doi:10.5565/rev/tradumatica.180

Cited by 7 publications

(5 citation statements)

References 22 publications

(12 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, according to the actual needs, the main working modules of the server and client and the main functions of each module are introduced in detail [11]. Based on the research of natural language processing, the literature designed a new method for translating English poetry into Chinese, and selected target poetry for experimental verification [12]. Through the analysis of research data, the task of translating English poetry into Chinese classical poetry was innovatively divided into machine translation stage and poetry generation stage.…”

Section: Related Workmentioning

confidence: 99%

Research on interactive system of Chinese-English translation model in cloud computing environment based on deep learning

Mai¹,

Yuan²

2023

Preprint

View full text Add to dashboard Cite

At present, human translation is characterized by low efficiency, high cost, high consumption of resources and time, so it is urgent to study automatic translation technology to meet the needs of information interaction and language communication in various countries under the background of economic globalization. This topic has also become a hot issue in the field of translation. After a long period of development, machine translation technology has gradually become popular and widely used, replacing human translation technology as the mainstream technology. Therefore, this paper implements the construction of an interactive system of English Chinese bilingual translation model based on cloud computing environment by introducing deep learning algorithm. The system can learn by itself on the basis of analyzing source documents, and predict target translation output by extracting features. The system is equipped with a translation engine based on the data source, which can realize interactive translation, and the final output can be achieved by processing the predicted translation output and based on the translator's understanding. Through the design of simulation experiments for system detection, the results show that the Chinese English translation model system has a high translation quality. By comparing it with the baseline system, it can be seen that both of them can translate sentences normally in 8 PR cycles (PR * 8, about 18% KSMR), and the data set improvement rate is about + 35 BLEU, that is, 76 BLEU is finally achieved. This proves that users can maintain the translation accuracy while reducing the number of effective interactions by using the optimized translation model to translate the target text, showing the effectiveness. In this paper, an interactive Chinese English translation system is designed by combining deep learning with cloud computing.

show abstract

Section: Related Workmentioning

confidence: 99%

Research on interactive system of Chinese-English translation model in cloud computing environment based on deep learning

Mai¹,

Yuan²

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…On one hand, AR [14][15][16] allows for the study of a new hybrid workflow and observes how it affects efficiency in terms of both speed and accuracy. On the other hand, the notion of TX [17], as well as studies about multimodality in translator-computer interaction [18][19][20] have informed the development and testing of ISV. This paved the way for the notion of Subtitler Experience (SUBX), which not only examines subtitler themselves, but also their work processes, work environments and their evaluation of suggested techniques and workflows.…”

Section: Related Workmentioning

confidence: 99%

Introducing Speech Recognition in Non-live Subtitling to Enhance the Subtitler Experience

Braun,

Davitti

2023

Proceedings of the International Conference on Human-Informed Translation and Interpreting Technology 2023

View full text Add to dashboard Cite

Interlingual Subtitle Voicing (ISV) is a new technique that focuses on using speech recognition (SR), rather than traditional keyboard-based techniques for the creation of non-live subtitles. SR has successfully been incorporated into intralingual live subtitling environments for the purposes of accessibility in major languages (real-time subtitles for the deaf and hard of hearing). However, ithas not yet been integrated as a helpful tool for the translation of non-live subtitles to any great and meaningful extent, especially for lower resourced languages like Croatian. This paper presents selected results from a larger PhD study entitled 'Interlingual Subtitle Voicing: A New Technique for the Creation of Interlingual Subtitles, A Case Study in Croatian'. More specifically, the paper focuses on the second supporting research question that explores participants feedback about the ISV technique, as a novel workflow element, and the accompanying technology. To explore this technique, purpose-made subtitling software was created, namely SpeakSubz. The constant enhancements of the tool akin to software updates are informed by participants' empirical results and qualitative feedback and shaped by subtitlers' needs. Some of the feedback from the main ISV study is presented in this paper.

show abstract

“…However, this time, we will provide the participants with various functionalities and measure and test what they prefer the most and why so that the tool can be customised even more in future. These will be explored under the concept of subtitler experience (SUBX) introduced in the ISV study, stemming from translator experience -(TX) [9][10][11], the term that Zapata derived from the general user experience (UX). In short, SpeakSubz will be explored not only as a training and testing, as well as a professional tool but also as an ergonomic one that enables subtitlers to work in more comfortable environments, away from the traditional keyboard-desk setting.…”

Section: Future Developmentmentioning

confidence: 99%

Developing a Customisable Subtitling Tool Based on Academic Research and User Needs

Radić

2023

Proceedings of the International Conference on Human-Informed Translation and Interpreting Technology 2023

View full text Add to dashboard Cite

SpeakSubz is a tool for translating non-live subtitles primarily relying on Google's speech recognition technology: Google Voice Typing. This specialised software also includes functionalities that make it a viable tool for academic research on various topics related to subtitling and voicing/respeaking. It was used as a tool within a larger doctoral study called 'Interlingual Subtitle Voicing: A New Technique for the Creation of Interlingual Subtitles, A Case Study in Croatian'. This study aimed to measure speech recognition accuracy for Croatian subtitles, the duration of various elements of a subtitling workflow, and, ultimately, to assess participants' reception of the technique and the tool and elicit their feedback for its future development. The tool is being developed based on academic scholarship, industry insights and, most importantly, subtitlers' needs. Within the framework of action research and the notion of subtitler experience and as highlighted in this paper, the tool is developed in cycles akin to software updates. In each cycle, a major new variable is introduced and tested with other minor changes related to either functionality or the interface. This paper will also highlight some of the most relevant functionalities that distinguish the current version of SpeakSubz from similar tools. The goal is to create a customisable tool for human-informed translation of subtitles that can be used for training and research in academia as well as professional environments.

show abstract

Translating On the Go? Investigating the Potential of Multimodal Mobile Devices for Interactive Translation Dictation

Cited by 7 publications

References 22 publications

Research on interactive system of Chinese-English translation model in cloud computing environment based on deep learning

Research on interactive system of Chinese-English translation model in cloud computing environment based on deep learning

Introducing Speech Recognition in Non-live Subtitling to Enhance the Subtitler Experience

Developing a Customisable Subtitling Tool Based on Academic Research and User Needs

Contact Info

Product

Resources

About