Speech Recognition

SMILE = Speech & Music Interpretation by Large Space Extraction openSMILE is a fast, real-time (audio) feature extraction utility for automatic speech, music and paralinguistic recognition research developed at TUM in the scope of the EU-project SEMA

EMU is a collection of software tools for the creation, manipulation and analysis of speech databases. At the core of EMU is a database search engine which allows queries based on the sequential and hierarchical structure of the annotations.

A speech synthesis and recognition library that is cross-platform, accessible from Java and C++, and has a very small API. Uses CMU Sphinx4 and FreeTTS internally.


Platforms: Windows, Mac, Linux

You can use Apple's speech synthesizer to easily create audio files that you can put on your iPod. * Make podcasts of blogs or other web pages. * Make your own "audio books" from downloadable free e-texts of books. * Create sound files saying every track in a playlist, so you can get a DJ on...


Platforms: Mac

The two-step noise reduction (TSNR) technique removes the annoying reverberation effect while maintaining the benefits of the decision-directed approach. However, classic short-time noise reduction techniques, including TSNR, introduce harmonic distortion in the enhanced speech. To overcome this...


Platforms: Matlab

This is a simple method for silence removal and segmentation of audio streams that contain speech. The method is based in two simple audio features (signal energy and spectral centroid). As long as the feature sequences are extracted, as thresholding approach is applied on those sequence, in...


Platforms: Matlab

the entry file is sharks.m which gives the graphical interface for software. the recognition rate was very good in MFCC.


Platforms: Matlab

The following zip file contains two routines for analysis/synthesis of HNM.HNM is a analysis/synthesis model of speech,like classical LPC model.Due to the limitation of my ability,i only implement a simply version of HNM,so welcome for somebody to improve on it.Usage:analysis:...


Platforms: Matlab

Character Recognition Using Neural NetworksSteps to use this GUI.1. Open the GUI figure, run it. (accept the matlab to change its directory to new location where the file is stored)2. First we need to teach Character to computer. For this type the Character in the textbox space provided and press...


Platforms: Matlab

Speech analysis and parameter extractionShort-term analysis, frames and windowsTime-domain analysis: energy, zero-crossings, statistic parameters, autocorrelationFrequency-domain analysis: spectra and spectrogramsCepstral analysisLinear prediction analysisPitch and formant estimationto run the...


Platforms: Matlab

Swift is an Asterisk application module for using the Cepstral Swift Text-To-Speech (TTS) Engine in Asterisk. You need to download and install one of the Cepstral Voices first. Voices are available for Mac OS-X, Linux, Windows and WindowsCE in several languages like English, Spanish, German,...


Platforms: Mac

OO Text To Speech is a text-to speech macro for OpenOffice.org. It's a syllable analyzer: using a reading motor, it reads a document and translates it into a vocal message. About OpenOffice OpenOffice.org is a multiplatform and multilingual office suite and an open-source project. Compatible...


Platforms: *nix

Talking Translator 1.0 is a small and easy to use text to speech Language Translator. It can Translate up to 150 English Words to 5 foreign languages and back. These Languages include French, German, Italian, Portuguese, Spanish. By utilizing MS Agent Technology it can also read the translation...


Platforms: Windows

v(1.0) fSC-Net - Win Neural Net Fuzzy Pattern Recognition. Quick, hassle-free automatic construction of Neural Networks. Incremental learning. Support of fuzzy logic. Hybrid symbolicconnectionist representation. Complete graphical support of training and testing. Point and click recall of network...


Platforms: Windows

Develop high performance, trouble free barcode recognition and image manipulation applications, in VB, C or Delphi.Production Quality Tools for Data Capture - ClearImage tools offer outstanding performance. They can rapidly recognize any number of barcodes, in any orientation on an image....


Platforms: Windows

SpeakOut is a text to speech software that can read any text or a text file for you. It can monitor windows clipboard and read the content automatically. A great freeware that cost nothing!Read any text. Read text file. Monitor the clipboard and automatically read.


Platforms: Windows

Palm PR, Intertraff number plate recognition software, runs on any Microsoft Windows 2003 PDA. Through a Compact Flash Camera, Palm PR analyses continuously the live picture looking for number plates. Once a vehicle plate is detected, the number is recognized using a series of complex...


Platforms: Windows CE

Language Reader takes advantage of existing speech technologies, provides a richer on-screen reading experience with multilingual voices enabled. Supported voices are English, French, German, Italian, Spanish, Portuguese, Dutch, Russian, Japanese, Korean. You can select text using your...


Platforms: Windows

Ear training music app and virtual piano to help you learn perfect pitch, test your aural note recognition and be a better musician. Features a realistic polyphonic piano sound and near full-size piano keyboard for playing music. Absolute Pitch is a musical ear trainer that uses a unique...


Platforms: Windows, Windows 8, Windows 7

Convert your scanned images to text files or Word documents with SimpleOCR--the OCR (Optical Character Recognition) application that is completely free. SimpleOCR is also a royalty-free developer toolkit (aka SDK or API) that you may use to add OCR to your custom software application....


Platforms: Windows