background preloader

CMU Sphinx - Speech Recognition Toolkit

CMU Sphinx - Speech Recognition Toolkit
Published on April 8, 2014 Personal assistants are hot these days. Open source personal assistant is a dream for many developers. Recently released Jasper makes it really easy to install personal assistant on Raspberry Pi and use it for custom voice commands, information retrieval and so on. Jasper is written in Python and can be extended through the API. More importantly, Jasper uses CMUSphinx for offline speech recognition, so much waited capability for assistant developers.

http://cmusphinx.sourceforge.net/

Related:  Speech Recognition

Tutorial - ros-pocketsphinx-speech-recognition-tutorial - One-sentence summary of this page. - ROS pocketsphinx speech recognition tutorial ROS/Pocketsphinx Speech Recognition Tutorial Part 1) Install sfml audio from SFML (simple and fast multimedia library) is a C++ API that provides you low and high level access to graphics, input, audio, etc. We will use this as our wav file player. This is the same mechanism utilized by Garratt Gallagher from his kinect piano play demo. I have modified the wav playing section of Garratt’s code so that it can be invoked on the command line and takes the path to any wav file as an easy mechanism for playing wav files.

HomeAlarmPlus Pi Latest update: Friday, November 8, 2013This is an open source home alarm monitoring system using Raspberry Pi, Netduino Plus, ATtiny 85 and a typical home alarm system. This implementation could be used in conjunction with the PC5010 Digital Security Controls (DSC) PowerSeries Security System control panel and sensors. Tested with Netduino Plus 1 running .NET Micro Framework 4.2 (QFE1 or QFE2) and Raspberry Pi Model A running Debian GNU/Linux 7.0 (wheezy). Previous ImplementationWhen I first started HomeAlarmPlus on February 2012 my intent was to have a simple home alarm monitoring system and learn more about microcontrollers. As the knowledge kept growing, also the complexity of the circuitry, system and requirements. Then Raspberry Pi complemented the existing project by using full capability of Apache Web server.

Later Terminator: We’re Nowhere Near Artificial Brains I can feel it in the air, so thick I can taste it. Can you? It’s the we’re-going-to-build-an-artificial-brain-at-any-moment feeling. It’s exuded into the atmosphere from news media plumes (“IBM Aims to Build Artificial Human Brain Within 10 Years”) and science-fiction movie fountains…and also from science research itself, including projects like Blue Brain and IBM’s SyNAPSE. For example, here’s a recent press release about the latter: EasyVR Shield - Voice Recognition Shield Description: Do you make time to talk to your Arduino? Maybe you should! The EasyVR Shield 2.0 is a voice recognition shield for Arduino boards integrating an EasyVR module.

Voice commands / speech to and from robot? answered Feb 22 '11 It's quite experimental and definitely not documented, but we have been using PocketSphinx to do speech recognition with ROS. See the cwru_voice package for source. If you run the voice.launch file (after changing some of the hardcoded model paths appropriately in whichever node it launches), you should be able to get certain keywords out on the "chatter" topic. motion_guide This version of the Guide is made for inclusion in the Motion download package for off line reading. If you read this document from the distribution package of Motion or from some not up to date mirror you should know that the URL for the always up to date version is If you are already on the new TWiki based Motion site clicking the link just mentioned will lead you to the index page for the Motion Guide documents. This topic consists of the following subtopics: MotionOverview, KnownProblems, InstallOverview, PrepareInstall, ConfigureScript, MakeInstall, UpgradingFromOlderVersion, RunningMotionConfigFiles, CommandLineOptions, ConfigFileOptions, SignalsKill, ErrorLogging, CaptureDeviceOptions, MotionDetectionSettings, ImageFileOutput, TuningMotion, MpegFilmsFFmpeg, SnapshotsWebCam, TextFeatures, AdvancedFilenames, ConversionSpecifiers, WebcamServer, RemoteControlHttp, ExternalCommands, TrackingControl, UsingDatabases, LoopbackDevice. Motion Overview

IBM simulates 530 billon neurons, 100 trillion synapses on supercomputer A network of neurosynaptic cores derived from long-distance wiring in the monkey brain: Neuro-synaptic cores are locally clustered into brain-inspired regions, and each core is represented as an individual point along the ring. Arcs are drawn from a source core to a destination core with an edge color defined by the color assigned to the source core. (Credit: IBM) Announced in 2008, DARPA’s SyNAPSE program calls for developing electronic neuromorphic (brain-simulation) machine technology that scales to biological levels, using a cognitive computing architecture with 1010 neurons (10 billion) and 1014 synapses (100 trillion, based on estimates of the number of synapses in the human brain) to develop electronic neuromorphic machine technology that scales to biological levels.” Simulating 10 billion neurons and 100 trillion synapses on most powerful supercomputer Neurosynaptic core (credit: IBM)

ØMQ - The Guide - ØMQ - The Guide By Pieter Hintjens, CEO of iMatix Please use the issue tracker for all comments and errata. This version covers the latest stable release of ZeroMQ (3.2). If you are using older versions of ZeroMQ then some of the examples and explanations won't be accurate. The Guide is originally in C, but also in PHP, Python, Lua, and Haxe.

Q-learning Q-learning is a model-free reinforcement learning technique. Specifically, Q-learning can be used to find an optimal action-selection policy for any given (finite) Markov decision process (MDP). It works by learning an action-value function that ultimately gives the expected utility of taking a given action in a given state and following the optimal policy thereafter. STAPLES SecurityMan® SM-80 Wireless Wide-Angle PIR Motion Sensor for Air-Alarm System This Web site is intended for use by US residents only. See International Sites. See our delivery policy for full details. Copyright 1998-2014, Staples, Inc., All Rights Reserved. Site Map | Privacy Policy | AdChoices

Model Suggests Link between Intelligence and Entropy +Enlarge image A. Wissner-Gross/Harvard Univ. & MIT A. Linux compatible Foscam FI8905W/FI8909W/FI8910W IP Wireless IR NetCams References Quick Looks Works with Linux - No drivers requiredMjpeg streamJpeg snapshotTwo resolutions: 640x480, 320x240Snapshots are the same as the set streaming resolutionBoth Mirror and Flip optionsBuilt-in web server using only javascriptFull functionality with Firefox, Opera, ChromeMultiple user/pass settings for viewing/control/settingsManual focus Discussion

Related:  Herramientas de voz para monitoreoVoice/Text recognition