Search Results for "speech"

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference. It includes a deep learning inference optimizer and runtime that delivers low latency and high throughput for deep learning inference applications. TensorRT-based applications perform up to 40X faster than CPU-only platforms during inference. With TensorRT, you can optimize neural network models trained in all major frameworks, calibrate for lower precision with high accuracy, and deploy to hyperscale data centers,...

The tool provides a simple TCP/UDP interface to let a remote machine perform TTS outputs.

linViex is a graphical programming environment for home automation tasks and other applications. It supports remote controls, sensor devices, power switches/dimmers, e-mail, text-to-speech conversion, media players and many more. Graphic symbols of functional objects can be interconnected to exchange and process data.

Flashlight is a fast, flexible machine learning library written entirely in C++ by Facebook AI Research and the creators of Torch, TensorFlow, Eigen, and Deep Speech. Native support in C++ and simple extensibility make Flashlight a powerful research framework that's hackable to its core and enables fast iteration on new experimental setups and algorithms with little unopinionated and without sacrificing performance. In a single repository, Flashlight provides apps for research across multiple domains. ...

As a general data structure with strong expressive ability, graphs can be used to describe many problems in the real world, such as user networks in social scenarios, user and commodity networks in e-commerce scenarios, communication networks in telecom scenarios, and transaction networks in financial scenarios. and drug molecule networks in medical scenarios, etc. Data in the fields of text, speech, and images is easier to process into a grid-like type of Euclidean space, which is suitable for processing by existing deep learning models. Graph is a data type in non-Euclidean space and cannot be directly applied to existing methods, requiring a specially designed graph neural network system. Graph-based learning methods such as graph neural networks combine end-to-end learning with inductive reasoning, and are expected to solve a series of problems such as relational reasoning and interpretability that deep learning cannot handle.

OpenAuto is an AndroidAuto(tm) headunit emulator based on aasdk library and Qt libraries. Main goal is to run this application on the RaspberryPI 3 board computer smoothly. The OpenAuto Pro is the most advanced Raspberry Pi-based, custom head-unit solution ready to retrofit your vehicle. The main functionality of the OpenAuto Pro software is to bring Users access to modern head-unit features like Bluetooth Hands-Free Profile, music streaming, integrated media player, navigation via Android...

Caffe is a deep learning framework made with expression, speed, and modularity in mind. It is developed by Berkeley AI Research (BAIR) and by community contributors. Yangqing Jia created the project during his PhD at UC Berkeley. Caffe is released under the BSD 2-Clause license. Expressive architecture encourages application and innovation. Models and optimization are defined by configuration without hard-coding. Switch between CPU and GPU by setting a single flag to train on a GPU machine...

BTK contains C++ and Python libraries that implement speech processing and microphone array techniques such as speech feature extraction, speech enhancement, speaker tracking, beamforming, dereverberation and echo cancellation algorithms. The Millennium ASR provides C++ and python libraries for automatic speech recognition. The Millennium ASR implements a weighted finite state transducer (WFST) decoder, training and adaptation methods.

RNNLIB is a recurrent neural network library for sequence learning problems. Applicable to most types of spatiotemporal data, it has proven particularly effective for speech and handwriting recognition. full installation and usage instructions given at http://sourceforge.net/p/rnnl/wiki/Home/

A JNI wrapper for pjsip. You can use this wrapper to develop Java applications using the pjsip library. At the moment only the pjsua API is implemented. If you would like to obtain a commercial license, or need customisations, please contact us.

http://www.open-source-soft.narod.ru/VoiceDetector.7z It voice detector class,for detecting human speech, anti noise, anti tones, standard C++, completely cross-platform by recompilation.

WOSH is a multi-platform message-oriented middleware written in ANSI C++. Service oriented architecture, designed for network distributed computing. Already working: Audio multimedia, X10, remote control (WinMobile, GTalk) and much more..

QWave: Qt-based waveform display and audio playback class library.

Acoustic model developed using acoustic data recorded by native Hindi speakers.

Speech based User Interface Components Library for Java is a project to create Java controls and applications that can be used not only by literate people but also by non-literates. Speech and visual element with minimal text is used to create components

BladeWareVXML is a portable VoiceXML 2.1 interpreter that is an enhanced version (performance, usability and integration) of OpenVXI. A commercial version, with documentation, sample code, and support options, is available from the Commetrex Website.

converts SAPI speech commands to keystrokes

The AccessMusic project provides a set of tools for creating accessible music which are freely available to download. These tools allow you to convert music scores from traditional western music notation to formats for the Blind and visually impaired.

OpenExposition is a library for automatic construction of user interfaces. After specifying variables/methods that should be exposed, the library automatically generates graphical (FLTK, Cocoa), programmatic (Python, MAX/MSP), and speech-based UI.

The Lazybones project is a server and a collection of clients. It allows one person to voice control multiple machines. Designed for software developers and sys admins, Lazybones speeds up redundant and/or complex tasks.

The Open VXI VoiceXML interpreter is a portable open source library that interprets the VoiceXML dialog markup language. It is designed to serve as a reference for parties interested in understanding how VoiceXML markup might be executed.

Win32 COM Server DLL implements a generic drawing engine for rendering HTML-like markup into any Device Context. The library features stunning, markup-based custom tooltips and menus for Windows applications, speech integration, application skins, etc.

Time of day service over telephone using Voicent Gateway, a VoiceXML gateway that specially designed for voice modems. A Free version is available for download at http://www.voicent.com/download. Sample code for interactive telephony applications.

The Pawn will make it possibly for you to tell the computer exactly what you would like it to do. Fiction. No its reality now. The highly customizable slackware will be the base for Pawn.

Libmluv is a C/C++ programmers library to provide the Czech text-to-speech synthesis and should be able to do transcription of Czech text to string of phonemes.