Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userVUS at IWSLT 2021: A Finetuned Pipeline for Offline Speech Translation
VUS في IWSLT 2021: خط أنابيب Finetuned للترجمة الكلام في وضع عدم الاتصال
155
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
في هذا التقرير الفني، وصفنا أن خط أنابيب ASR-MT المصنف الذي تم ضبطه على المهمة المشتركة IWSLT.نقوم بإزالة عينات الكلام الأقل فائدة عن طريق فحص WER مع نموذج ASR، وتدريب أحدث وحدة ASR القائمة على WAV2VEC ومقرها المحولات بناء على البيانات المرتبطة.بالإضافة إلى ذلك، نقوم بتخفيف Errata التي يمكن أن تتداخل مع عملية الترجمة الآلية واستخدامها لتدريب وحدة MT القائمة على المحولات.أخيرا، في مرحلة الاستدلال الفعلي، نستخدم نموذج اكتشاف حدود الجملة المدرب مع بيانات مقيدة لدمج مخرجات ASR بشكل صحيح في جمل كاملة.تتم معالجة الجمل المدمجة باستخدام جزء من الكلام.يتم تحقيق النتيجة النهائية من قبل وحدة MT المدربة.يعرض الأداء باستخدام مجموعة DEV Bleu 20.37، وهذا النموذج يسجل أداء Bleu 20.9 مع مجموعة الاختبار.
In this technical report, we describe the fine-tuned ASR-MT pipeline used for the IWSLT shared task. We remove less useful speech samples by checking WER with an ASR model, and further train a wav2vec and Transformers-based ASR module based on the filtered data. In addition, we cleanse the errata that can interfere with the machine translation process and use it for Transformer-based MT module training. Finally, in the actual inference phase, we use a sentence boundary detection model trained with constrained data to properly merge fragment ASR outputs into full sentences. The merged sentences are post-processed using part of speech. The final result is yielded by the trained MT module. The performance using the dev set displays BLEU 20.37, and this model records the performance of BLEU 20.9 with the test set.
References used
https://aclanthology.org/
rate research
Read More
This paper describes KIT'submission to the IWSLT 2021 Offline Speech Translation Task. We describe a system in both cascaded condition and end-to-end condition. In the cascaded condition, we investigated different end-to-end architectures for the spe
ech recognition module. For the text segmentation module, we trained a small transformer-based model on high-quality monolingual data. For the translation module, our last year's neural machine translation model was reused. In the end-to-end condition, we improved our Speech Relative Transformer architecture to reach or even surpass the result of the cascade system.
This paper describes the ESPnet-ST group's IWSLT 2021 submission in the offline speech translation track. This year we made various efforts on training data, architecture, and audio segmentation. On the data side, we investigated sequence-level knowl
edge distillation (SeqKD) for end-to-end (E2E) speech translation. Specifically, we used multi-referenced SeqKD from multiple teachers trained on different amounts of bitext. On the architecture side, we adopted the Conformer encoder and the Multi-Decoder architecture, which equips dedicated decoders for speech recognition and translation tasks in a unified encoder-decoder model and enables search in both source and target language spaces during inference. We also significantly improved audio segmentation by using the pyannote.audio toolkit and merging multiple short segments for long context modeling. Experimental evaluations showed that each of them contributed to large improvements in translation performance. Our best E2E system combined all the above techniques with model ensembling and achieved 31.4 BLEU on the 2-ref of tst2021 and 21.2 BLEU and 19.3 BLEU on the two single references of tst2021.
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. Participants can decide whether to work
on constrained systems or unconstrained systems which can using external data. We create both cascaded and end-to-end speech translation constrained systems, using the provided data only. In the cascaded approach, we combine Conformer-based automatic speech recognition (ASR) with the Transformer-based neural machine translation (NMT). Our end-to-end direct speech translation systems use ASR pretrained encoder and multi-task decoders. The submitted systems are ensembled by different cascaded models.
This paper describes the submission of the NiuTrans end-to-end speech translation system for the IWSLT 2021 offline task, which translates from the English audio to German text directly without intermediate transcription. We use the Transformer-based
model architecture and enhance it by Conformer, relative position encoding, and stacked acoustic and textual encoding. To augment the training data, the English transcriptions are translated to German translations. Finally, we employ ensemble decoding to integrate the predictions from several models trained with the different datasets. Combining these techniques, we achieve 33.84 BLEU points on the MuST-C En-De test set, which shows the enormous potential of the end-to-end model.
The paper describes BUT's English to German offline speech translation (ST) systems developed for IWSLT2021. They are based on jointly trained Automatic Speech Recognition-Machine Translation models. Their performances is evaluated on MustC-Common te
st set. In this work, we study their efficiency from the perspective of having a large amount of separate ASR training data and MT training data, and a smaller amount of speech-translation training data. Large amounts of ASR and MT training data are utilized for pre-training the ASR and MT models. Speech-translation data is used to jointly optimize ASR-MT models by defining an end-to-end differentiable path from speech to translations. For this purpose, we use the internal continuous representations from the ASR-decoder as the input to MT module. We show that speech translation can be further improved by training the ASR-decoder jointly with the MT-module using large amount of text-only MT training data. We also show significant improvements by training an ASR module capable of generating punctuated text, rather than leaving the punctuation task to the MT module.
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
