Deep Learning Based TTS-STT Model with Transliteration for Indic Languages

Abstract: This paper introduces a new text-to-speech presentation from end-to-end (E2E-TTS) using toolkit called ESPnet-TTS, which is an open source extension. ESPnet speech processing tools kit. Various models come under ESPnet TTS TacoTron 2, Transformer TTS, and Fast Speech. This also provides recipes recommended by the Kaldi speech recognition tool kit (ASR). Recipes based on the composition combined with the ESPnet ASR recipe, which provides high performance. This toolkit also provides pre-trained models and samples of all recipes for users to use as a base .It works on TTS-STT and translation features for various indicator languages, with a strong focus on English, Marathi and Hindi. This paper also shows that neural sequence-to-sequence models find the state of the art or near the effects of the art state on existing databases. We also analyze some of the key design challenges that contribute to the development of a multilingual business translation system, which includes processing bilingual business data sets and evaluating multiple translation methods. The test result can be obtained using tokens and these test results show that our models can achieve modern performance compared to the latest LJ Speech tool kit data. Terms of Reference — Open source, end-to-end, text-to-speech

Download Full-text

MS-PyCloud: An open-source, cloud computing-based pipeline for LC-MS/MS data analysis

10.1101/320887 ◽

2018 ◽

Cited By ~ 2

Author(s):

Li Chen ◽

Bai Zhang ◽

Michael Schnaubelt ◽

Punit Shah ◽

Paul Aiyetan ◽

...

Keyword(s):

Cloud Computing ◽

Data Analysis ◽

Open Source ◽

High Performance ◽

Large Scale ◽

Rapid Development ◽

Data File ◽

Data Sets ◽

Proteomics Data ◽

Amazon Web Services

ABSTRACTRapid development and wide adoption of mass spectrometry-based proteomics technologies have empowered scientists to study proteins and their modifications in complex samples on a large scale. This progress has also created unprecedented challenges for individual labs to store, manage and analyze proteomics data, both in the cost for proprietary software and high-performance computing, and the long processing time that discourages on-the-fly changes of data processing settings required in explorative and discovery analysis. We developed an open-source, cloud computing-based pipeline, MS-PyCloud, with graphical user interface (GUI) support, for LC-MS/MS data analysis. The major components of this pipeline include data file integrity validation, MS/MS database search for spectral assignment, false discovery rate estimation, protein inference, determination of protein post-translation modifications, and quantitation of specific (modified) peptides and proteins. To ensure the transparency and reproducibility of data analysis, MS-PyCloud includes open source software tools with comprehensive testing and versioning for spectrum assignments. Leveraging public cloud computing infrastructure via Amazon Web Services (AWS), MS-PyCloud scales seamlessly based on analysis demand to achieve fast and efficient performance. Application of the pipeline to the analysis of large-scale iTRAQ/TMT LC-MS/MS data sets demonstrated the effectiveness and high performance of MS-PyCloud. The software can be downloaded at: https://bitbucket.org/mschnau/ms-pycloud/downloads/

Download Full-text

Espnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech Toolkit

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) ◽

10.1109/icassp40776.2020.9053512 ◽

2020 ◽

Cited By ~ 5

Author(s):

Tomoki Hayashi ◽

Ryuichi Yamamoto ◽

Katsuki Inoue ◽

Takenori Yoshimura ◽

Shinji Watanabe ◽

...

Keyword(s):

Open Source ◽

Text To Speech ◽

End To End

Download Full-text

Generating High-Performance FPGA Accelerator Designs for Big Data Analytics with Fletcher and Apache Arrow

Journal of Signal Processing Systems ◽

10.1007/s11265-021-01650-6 ◽

2021 ◽

Author(s):

Johan Peltenburg ◽

Jeroen van Straten ◽

Matthijs Brobbel ◽

Zaid Al-Ars ◽

H. Peter Hofstee

Keyword(s):

Big Data ◽

Open Source ◽

Data Analytics ◽

High Performance ◽

Big Data Analytics ◽

Data Sets ◽

Zero Copy ◽

Generic Architecture ◽

Near Term ◽

Time Systems

AbstractAs big data analytics systems are squeezing out the last bits of performance of CPUs and GPUs, the next near-term and widely available alternative industry is considering for higher performance in the data center and cloud is the FPGA accelerator. We discuss several challenges a developer has to face when designing and integrating FPGA accelerators for big data analytics pipelines. On the software side, we observe complex run-time systems, hardware-unfriendly in-memory layouts of data sets, and (de)serialization overhead. On the hardware side, we observe a relative lack of platform-agnostic open-source tooling, a high design effort for data structure-specific interfaces, and a high design effort for infrastructure. The open source Fletcher framework addresses these challenges. It is built on top of Apache Arrow, which provides a common, hardware-friendly in-memory format to allow zero-copy communication of large tabular data, preventing (de)serialization overhead. Fletcher adds FPGA accelerators to the list of over eleven supported software languages. To deal with the hardware challenges, we present Arrow-specific components, providing easy-to-use, high-performance interfaces to accelerated kernels. The components are combined based on a generic architecture that is specialized according to the application through an extensive infrastructure generation framework that is presented in this article. All generated hardware is vendor-agnostic, and software drivers add a platform-agnostic layer, allowing users to create portable implementations.

Download Full-text

Data Augmentation for Pipeline-Based Speech Translation

Frontiers in Artificial Intelligence and Applications - Human Language Technologies – The Baltic Perspective ◽

10.3233/faia200605 ◽

2020 ◽

Author(s):

Diego Alves ◽

Askars Salimbajevs ◽

Mārcis Pinnis

Keyword(s):

Speech Processing ◽

Data Augmentation ◽

System Development ◽

Recognition System ◽

Translation System ◽

Speech Translation ◽

Baseline System ◽

System Output ◽

Translation Methods ◽

Translation Systems

Pipeline-based speech translation methods may suffer from errors found in speech recognition system output. Therefore, it is crucial that machine translation systems are trained to be robust against such noise. In this paper, we propose two methods for parallel data augmentation for pipeline-based speech translation system development. The first method utilises a speech processing workflow to introduce errors and the second method generates commonly found suffix errors using a rule-based method. We show that the methods in combination allow significantly improving speech translation quality by 1.87 BLEU points over a baseline system.

Download Full-text

WikiSpeech – enabling open source text-to-speech for Wikipedia

10.21437/ssw.2016-16 ◽

2016 ◽

Author(s):

John Andersson ◽

Sebastian Berlin ◽

André Costa ◽

Harald Berthelsen ◽

Hanna Lindgren ◽

...

Keyword(s):

Open Source ◽

Text To Speech ◽

Source Text

Download Full-text

A High Performance Open-source Syringe Extruder Optimized for Extrusion and Retraction During FRESH 3D Bioprinting

HardwareX ◽

10.1016/j.ohx.2020.e00170 ◽

2021 ◽

pp. e00170

Author(s):

Joshua W. Tashman ◽

Daniel J. Shiwarski ◽

Adam W. Feinberg

Keyword(s):

Open Source ◽

High Performance ◽

3D Bioprinting

Download Full-text

An open source high-performance solution to extract surface water drainage networks from diverse terrain conditions

Cartography and Geographic Information Science ◽

10.1080/15230406.2017.1337524 ◽

2017 ◽

Vol 45 (4) ◽

pp. 319-328 ◽

Cited By ~ 2

Author(s):

Lawrence V. Stanislawski ◽

Kornelijus Survila ◽

Jeffrey Wendel ◽

Yan Liu ◽

Barbara P. Buttenfield

Keyword(s):

Surface Water ◽

Open Source ◽

High Performance ◽

Water Drainage ◽

Drainage Networks

Download Full-text

End-To-End Computer Vision Framework: An Open-Source Platform for Research and Education

Sensors ◽

10.3390/s21113691 ◽

2021 ◽

Vol 21 (11) ◽

pp. 3691

Author(s):

Ciprian Orhei ◽

Silviu Vert ◽

Muguras Mocofan ◽

Radu Vasiu

Keyword(s):

Machine Learning ◽

Image Processing ◽

Computer Vision ◽

Open Source ◽

Visual Processing ◽

Research Field ◽

Learning Models ◽

Research Activity ◽

End To End ◽

Machine Learning Models

Computer Vision is a cross-research field with the main purpose of understanding the surrounding environment as closely as possible to human perception. The image processing systems is continuously growing and expanding into more complex systems, usually tailored to the certain needs or applications it may serve. To better serve this purpose, research on the architecture and design of such systems is also important. We present the End-to-End Computer Vision Framework, an open-source solution that aims to support researchers and teachers within the image processing vast field. The framework has incorporated Computer Vision features and Machine Learning models that researchers can use. In the continuous need to add new Computer Vision algorithms for a day-to-day research activity, our proposed framework has an advantage given by the configurable and scalar architecture. Even if the main focus of the framework is on the Computer Vision processing pipeline, the framework offers solutions to incorporate even more complex activities, such as training Machine Learning models. EECVF aims to become a useful tool for learning activities in the Computer Vision field, as it allows the learner and the teacher to handle only the topics at hand, and not the interconnection necessary for visual processing flow.

Download Full-text