Filters








1,172 Hits in 6.1 sec

Generative Adversarial Text to Image Synthesis [article]

Scott Reed, Zeynep Akata, Xinchen Yan, Lajanugen Logeswaran, Bernt Schiele, Honglak Lee
<span title="2016-06-05">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
However, in recent years generic and powerful recurrent neural network architectures have been developed to learn discriminative text feature representations.  ...  Automatic synthesis of realistic images from text would be interesting and useful, but current AI systems are still far from this goal.  ...  Acknowledgments This work was supported in part by NSF CAREER IIS-1453651, ONR N00014-13-1-0762 and NSF CMMI-1266184.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1605.05396v2">arXiv:1605.05396v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4nqzfh6bcze6tklrdxnckv4hpy">fatcat:4nqzfh6bcze6tklrdxnckv4hpy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191015084757/https://arxiv.org/pdf/1605.05396v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/a9/12/a9124c87d1241fc1d638ae56b5a1872ba5d225ba.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1605.05396v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

ZM-Net: Real-time Zero-shot Image Manipulation Network [article]

Hao Wang, Xiaodan Liang, Hao Zhang, Dit-Yan Yeung, Eric P. Xing
<span title="2017-03-22">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we make the first attempt to address the zero-shot image manipulation task.  ...  To this end, we propose the Zero-shot Manipulation Net (ZM-Net), a fully-differentiable architecture that jointly optimizes an image-transformation network (TNet) and a parameter network (PNet).  ...  Fast Zero-shot Style Transfer.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1703.07255v2">arXiv:1703.07255v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hscxzyqenjftloxmysqj2ke52e">fatcat:hscxzyqenjftloxmysqj2ke52e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200825235730/https://arxiv.org/pdf/1703.07255v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e5/0f/e50fca18d522d723aad106b29e0fad43f17f9a8d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1703.07255v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Review of Text Style Transfer Based on Deep Learning [article]

Xiangyang Li, Guo Pu, Keyu Ming, Pu Li, Jie Wang, Yuxuan Wang
<span title="2020-12-30">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In addition, the article also introduces public data sets and evaluation indicators commonly used for text style transfer.  ...  In recent years, text style transfer is becoming a hot issue in natural language processing research.  ...  The model uses a multi-layer recurrent neural network (RNN) encoder and decoder. The encoder and decoder are three-layer bidirectional recurrent neural networks.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2005.02914v3">arXiv:2005.02914v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/oj36kqqctfb5hjanb4j7kn5ntq">fatcat:oj36kqqctfb5hjanb4j7kn5ntq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200514003022/https://arxiv.org/ftp/arxiv/papers/2005/2005.02914.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2005.02914v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

ConVoice: Real-Time Zero-Shot Voice Style Transfer with Convolutional Network [article]

Yurii Rebryk, Stanislav Beliaev
<span title="2020-05-15">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We propose a neural network for zero-shot voice conversion (VC) without any parallel or transcribed data.  ...  Our model is fully convolutional and non-autoregressive except for a small pre-trained recurrent neural network for speaker encoding.  ...  There are also models which map a source speech to a variable length output by using recurrent neural networks (RNNs) or attentionbased auto-regressive models [5, 6, 7] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2005.07815v1">arXiv:2005.07815v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/66yjqysuz5gxzbhiyj7wcz7oi4">fatcat:66yjqysuz5gxzbhiyj7wcz7oi4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200528224127/https://arxiv.org/pdf/2005.07815v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2005.07815v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Few Shot Adaptive Normalization Driven Multi-Speaker Speech Synthesis [article]

Neeraj Kumar, Srishti Goel, Ankur Narang, Brejesh Lall
<span title="2020-12-14">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Given an input text and a reference speech sample of an unseen person, FSM-SS can generate speech in that person's style in a few shot manner.  ...  Additionally, we demonstrate how the affine parameters of normalization help in capturing the prosodic features such as energy and fundamental frequency in a disentangled fashion and can be used to generate  ...  Our approach uses non-autoregressive deep neural networks based method instead of HMM-based speech generation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.07252v1">arXiv:2012.07252v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yn5npt4xu5dapjnenrlwdj7ei4">fatcat:yn5npt4xu5dapjnenrlwdj7ei4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201218033602/https://arxiv.org/pdf/2012.07252v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/9c/7a/9c7aa4985a70e8893f27e4ffaceae5b97927a982.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.07252v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Transfer Learning for Multi-lingual Tasks – a Survey [article]

Amir Reza Jafari, Behnam Heidary, Reza Farahbakhsh, Mostafa Salehi, Mahdi Jalili
<span title="2021-08-28">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this survey, we provide a comprehensive overview of the existing literature with a focus on transfer learning techniques in multilingual tasks.  ...  In this era, understanding cross languages content and multilingualism in natural language processing (NLP) are hot topics, and multiple efforts have tried to leverage existing technologies in NLP to tackle  ...  The influence of the main types of neural networks in NLP started with the introduction of Recurrent neural networks (RNNs) [67] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.02052v1">arXiv:2110.02052v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/42k7enhfynfgbabihvgf5qpa2m">fatcat:42k7enhfynfgbabihvgf5qpa2m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211007030747/https://arxiv.org/pdf/2110.02052v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/89/a4/89a4f4d1f8c93da85d829a1acfe8cafea2b50c00.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.02052v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Zero-Shot Activity Recognition with Videos [article]

Evin Pinar Ornek
<span title="2020-01-22">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we examined the zero-shot activity recognition task with the usage of videos.  ...  On the visual side, we used activity videos and a state-of-the-art 3D convolutional action recognition network to extract the features. On the textual side, we worked with GloVe word embeddings.  ...  This loss is commonly used in computer vision tasks to transfer the artistic style of an image to another image.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.02265v1">arXiv:2002.02265v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/umbgctxyzzbvhcfrkg7dgfnciq">fatcat:umbgctxyzzbvhcfrkg7dgfnciq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321070426/https://arxiv.org/pdf/2002.02265v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.02265v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Survey on Zero-Shot Detection

Deeshant Singh
<span title="2020-12-31">2020</span> <i title="International Journal for Research in Applied Science and Engineering Technology (IJRASET)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/hsp44774azcezeyiq4kuzpfh5a" style="color: black;">International Journal for Research in Applied Science and Engineering Technology</a> </i> &nbsp;
Accordingly, in this paper we are going to explain to you about zero-shot object detection techniques where how this zero-shot object detection technique recognizes the object and arranges the data in  ...  The algorithm used in zero-shot training like granting, generative approaches. where in granting approaches output a hard decision, but emitting a soft probabilistic decision further improves the accuracy  ...  Despite advances, in particular, using deep neural networks, there is no multi-label learning algorithm that can achieve all these goals [5] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.22214/ijraset.2020.32426">doi:10.22214/ijraset.2020.32426</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7i4qx44hfbhqff2owvrun5uvme">fatcat:7i4qx44hfbhqff2owvrun5uvme</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201213043917/https://www.ijraset.com/fileserve.php?FID=32426" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/3a/e1/3ae11bcfba591209d0a7dee8866866f066e7a7a7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.22214/ijraset.2020.32426"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

Neural Entity Linking: A Survey of Models Based on Deep Learning [article]

Ozge Sevgili, Artem Shelmanov, Mikhail Arkhipov, Alexander Panchenko, Chris Biemann
<span title="2021-08-25">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
techniques including zero-shot and distant supervision methods, and cross-lingual approaches.  ...  In this survey, we provide a comprehensive description of recent neural entity linking (EL) systems developed since 2015 as a result of the "deep learning revolution" in NLP.  ...  The work of Artem Shelmanov in the current study (preparation of sections related to application of entity linking to neural language models, entity ranking, contextmention encoding, and overall harmonization  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.00575v3">arXiv:2006.00575v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ra3kwc4tmbfhlmgtlevkcshcqq">fatcat:ra3kwc4tmbfhlmgtlevkcshcqq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210830072050/https://arxiv.org/pdf/2006.00575v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/c2/c9/c2c9262c85bfbe0dfcf6c2431dc9c6bc2da8d07d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.00575v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Neural entity linking: A survey of models based on deep learning

Özge Sevgili, Artem Shelmanov, Mikhail Arkhipov, Alexander Panchenko, Chris Biemann, Mehwish Alam, Davide Buscaldi, Michael Cochez, Francesco Osborne, Diego Reforgiato Recupero, Harald Sack
<span title="2022-03-23">2022</span> <i title="IOS Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/pcapks3huberdozbvfqowysuly" style="color: black;">Semantic Web Journal</a> </i> &nbsp;
modifications of this general architecture are grouped by several common themes: joint entity mention detection and disambiguation, models for global linking, domain-independent techniques including zero-shot  ...  This survey presents a comprehensive description of recent neural entity linking (EL) systems developed since 2015 as a result of the "deep learning revolution" in natural language processing.  ...  The work of Artem Shelmanov in the current study (preparation of sections related to application of entity linking to neural language models, entity ranking, context-mention encoding, and overall harmonization  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3233/sw-222986">doi:10.3233/sw-222986</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6gwmbtev7ngbliovf6cpf5hyde">fatcat:6gwmbtev7ngbliovf6cpf5hyde</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220421070535/https://content.iospress.com/download/semantic-web/sw222986?id=semantic-web%2Fsw222986" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3233/sw-222986"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

2021 Index IEEE Transactions on Multimedia Vol. 23

<span title="">2021</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/sbzicoknnzc3tjljn7ifvwpooi" style="color: black;">IEEE transactions on multimedia</a> </i> &nbsp;
-that appeared in this periodical during 2021, and items from previous years that were commented upon or corrected in 2021.  ...  Note that the item title is found only under the primary entry in the Author Index.  ...  ., +, TMM 2021 3362-3376 StyleGuide: Zero-Shot Sketch-Based Image Retrieval Using Style-Guided Image Generation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tmm.2022.3141947">doi:10.1109/tmm.2022.3141947</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lil2nf3vd5ehbfgtslulu7y3lq">fatcat:lil2nf3vd5ehbfgtslulu7y3lq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220112070754/https://ieeexplore.ieee.org/ielx7/6046/9296985/09677625.pdf?tp=&amp;arnumber=9677625&amp;isnumber=9296985&amp;ref=" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/72/98/7298e0836b658eb4f1e43b1ba4059c50a3847dba.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tmm.2022.3141947"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Semantic Image Synthesis via Adversarial Learning [article]

Hao Dong, Simiao Yu, Chao Wu, Yike Guo
<span title="2017-07-21">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we propose a way of synthesizing realistic images directly with natural language description, which has many useful applications, e.g. intelligent image manipulation.  ...  To achieve this, we proposed an end-to-end neural architecture that leverages adversarial learning to automatically learn implicit loss functions, which are optimized to fulfill the aforementioned two  ...  Specifically, given pairs of image x and text t, we use a convolutional network φ and a recurrent network ϕ to encode image and text respectively.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1707.06873v1">arXiv:1707.06873v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/64xw3rnf7nc7zig5unzi74dfpa">fatcat:64xw3rnf7nc7zig5unzi74dfpa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200913220046/https://arxiv.org/pdf/1707.06873v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/bb/4e/bb4e1269aaa37c9caa71751279a81b9c4fef4b23.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1707.06873v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Survey on Neural Speech Synthesis [article]

Xu Tan, Tao Qin, Frank Soong, Tie-Yan Liu
<span title="2021-07-23">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
As the development of deep learning and artificial intelligence, neural network-based TTS has significantly improved the quality of synthesized speech in recent years.  ...  We focus on the key components in neural TTS, including text analysis, acoustic models and vocoders, and several advanced topics, including fast TTS, low-resource TTS, robust TTS, expressive TTS, and adaptive  ...  In near 2010s, as neural network and deep learning have achieved rapid progress, some works first introduce deep neural network into SPSS, such as deep neural network (DNN) based [426, 284] and recurrent  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.15561v3">arXiv:2106.15561v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pbrbs6xay5e4fhf4ewlp7qvybi">fatcat:pbrbs6xay5e4fhf4ewlp7qvybi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210727181001/https://arxiv.org/pdf/2106.15561v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/43/84/4384ff4ac7459d3045ff660b1772c975512701d9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.15561v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Brief Survey of Multilingual Neural Machine Translation [article]

Raj Dabre, Chenhui Chu, Anoop Kunchukuttan
<span title="2020-01-04">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
MNMT has been useful in improving translation quality as a result of knowledge transfer.  ...  We present a survey on multilingual neural machine translation (MNMT), which has gained a lot of traction in the recent years.  ...  A comparison of transformer and recurrent neural networks on multilingual neural machine translation. In Proceedings of the 27th International Conference on Computational Linguistics, pages 641-652.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1905.05395v3">arXiv:1905.05395v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cyufmt3y65bhjofvt5zeljahz4">fatcat:cyufmt3y65bhjofvt5zeljahz4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321010751/https://arxiv.org/pdf/1905.05395v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1905.05395v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Transfer Learning from Monolingual ASR to Transcription-free Cross-lingual Voice Conversion [article]

Che-Jui Chang
<span title="2020-09-30">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We experiment this on Voice Conversion Challenge 2020 datasets and show that our speaker-dependent conversion model outperforms the zero-shot baseline, achieving MOS of 3.83 and 3.54 in speech quality  ...  In this paper, we focus on knowledge transfer from monolin-gual ASR to cross-lingual VC, in order to address the con-tent mismatch problem.  ...  For instance, these papers [17, 12] are based on recurrent neural networks with attention mechanisms and transformers respectively.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.14668v1">arXiv:2009.14668v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2hr3hlezujbtxcffnj7scz4hua">fatcat:2hr3hlezujbtxcffnj7scz4hua</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201002095222/https://arxiv.org/ftp/arxiv/papers/2009/2009.14668.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.14668v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 1,172 results