Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userBTS: Back TranScription for Speech-to-Text Post-Processor using Text-to-Speech-to-Text
BTS: النسخ الخلفي للمعالج إلى النص إلى النص باستخدام النص إلى كلام إلى النص
236
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
مع وجود شعبية متزايدة للمتحدثين الذكية، مثل الأمازون اليكسا، أصبح الكلام أحد أهم طرق التفاعل بين الإنسان والحاسوب. يمكن القول إن التعرف التلقائي على التعرف على الكلام (ASR) هو العنصر الأكثر أهمية في هذه الأنظمة، حيث ينتشر أخطاء في التعرف على الكلام إلى مكونات المصب التي تتحلل بشكل كبير من تجربة المستخدم. طريقة بسيطة وفعالة لتحسين دقة التعرف على الكلام هي تطبيق ما بعد المعالج التلقائي نتيجة التعرف. ومع ذلك، فإن التدريب على معالج ما بعد البيع يتطلب شركة موازية تم إنشاؤها بواسطة Annwotators البشرية، وهي مكلفة وغير قابلة للتحجيم. لتخفيف هذه المشكلة، نقترح النسخ الخلفي (BTS)، وهي طريقة قائمة على الدنيوية التي يمكن أن تنشئ مثل هذه الشركة دون عمل بشري. باستخدام CORPUS RAW، يقوم BTS بتلف النص باستخدام أنظمة تحويل النص إلى كلام (TTS) ونص الكلام إلى النص (STT). بعد ذلك، يمكن تدريب نموذج ما بعد المعالجة على إعادة بناء النص الأصلي مع إعطاء المدخلات التالفة. تبين التقييمات الكمية والنوعية أن المعالج بعد المعالج المدرب باستخدام نهجنا فعال للغاية في إصلاح أخطاء التعرف على الكلام غير تافهة مثل سوء الكلمات الأجنبية. نقدم Corpus الموازي الذي تم إنشاؤه ومنصة ما بعد المعالجة لجعل نتائجنا متاحة للجمهور.
With the growing popularity of smart speakers, such as Amazon Alexa, speech is becoming one of the most important modes of human-computer interaction. Automatic speech recognition (ASR) is arguably the most critical component of such systems, as errors in speech recognition propagate to the downstream components and drastically degrade the user experience. A simple and effective way to improve the speech recognition accuracy is to apply automatic post-processor to the recognition result. However, training a post-processor requires parallel corpora created by human annotators, which are expensive and not scalable. To alleviate this problem, we propose Back TranScription (BTS), a denoising-based method that can create such corpora without human labor. Using a raw corpus, BTS corrupts the text using Text-to-Speech (TTS) and Speech-to-Text (STT) systems. Then, a post-processing model can be trained to reconstruct the original text given the corrupted input. Quantitative and qualitative evaluations show that a post-processor trained using our approach is highly effective in fixing non-trivial speech recognition errors such as mishandling foreign words. We present the generated parallel corpus and post-processing platform to make our results publicly available.
References used
https://aclanthology.org/
rate research
Read More
The National Virtual Translation Center (NVTC) seeks to acquire human language technology (HLT) tools that will facilitate its mission to provide verbatim English translations of foreign language audio and video files. In the text domain, NVTC has be
en using translation memory (TM) for some time and has reported on the incorporation of machine translation (MT) into that workflow (Miller et al., 2020). While we have explored the use of speech-totext (STT) and speech translation (ST) in the past (Tzoukermann and Miller, 2018), we have now invested in the creation of a substantial human-made corpus to thoroughly evaluate alternatives. Results from our analysis of this corpus and the performance of HLT tools point the way to the most promising ones to deploy in our workflow.
This paper describes our contribution to the Shared Task ReproGen by Belz et al. (2021), which investigates the reproducibility of human evaluations in the context of Natural Language Generation. We selected the paper Generation of Company descriptio
ns using concept-to-text and text-to-text deep models: data set collection and systems evaluation'' (Qader et al., 2018) and aimed to replicate, as closely to the original as possible, the human evaluation and the subsequent comparison between the human judgements and the automatic evaluation metrics. Here, we first outline the text generation task of the paper of Qader et al. (2018). Then, we document how we approached our replication of the paper's human evaluation. We also discuss the difficulties we encountered and which information was missing. Our replication has medium to strong correlation (0.66 Spearman overall) with the original results of Qader et al. (2018), but due to the missing information about how Qader et al. (2018) compared the human judgements with the metric scores, we have refrained from reproducing this comparison.
The transformer-based pre-trained language models have been tremendously successful in most of the conventional NLP tasks. But they often struggle in those tasks where numerical understanding is required. Some possible reasons can be the tokenizers a
nd pre-training objectives which are not specifically designed to learn and preserve numeracy. Here we investigate the ability of text-to-text transfer learning model (T5), which has outperformed its predecessors in the conventional NLP tasks, to learn numeracy. We consider four numeracy tasks: numeration, magnitude order prediction, finding minimum and maximum in a series, and sorting. We find that, although T5 models perform reasonably well in the interpolation setting, they struggle considerably in the extrapolation setting across all four tasks.
We motivate and propose a suite of simple but effective improvements for concept-to-text generation called SAPPHIRE: Set Augmentation and Post-hoc PHrase Infilling and REcombination. We demonstrate their effectiveness on generative commonsense reason
ing, a.k.a. the CommonGen task, through experiments using both BART and T5 models. Through extensive automatic and human evaluation, we show that SAPPHIRE noticeably improves model performance. An in-depth qualitative analysis illustrates that SAPPHIRE effectively addresses many issues of the baseline model generations, including lack of commonsense, insufficient specificity, and poor fluency.
Due to efficient end-to-end training and fluency in generated texts, several encoder-decoder framework-based models are recently proposed for data-to-text generations. Appropriate encoding of input data is a crucial part of such encoder-decoder model
s. However, only a few research works have concentrated on proper encoding methods. This paper presents a novel encoder-decoder based data-to-text generation model where the proposed encoder carefully encodes input data according to underlying structure of the data. The effectiveness of the proposed encoder is evaluated both extrinsically and intrinsically by shuffling input data without changing meaning of that data. For selecting appropriate content information in encoded data from encoder, the proposed model incorporates attention gates in the decoder. With extensive experiments on WikiBio and E2E dataset, we show that our model outperforms the state-of-the models and several standard baseline systems. Analysis of the model through component ablation tests and human evaluation endorse the proposed model as a well-grounded system.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
