•    Freeware
  •    Shareware
  •    Research
  •    Localization Tools 20
  •    Publications 617
  •    Validators 2
  •    Mobile Apps 22
  •    Fonts 31
  •    Guidelines/ Draft Standards 3
  •    Documents 13
  •    General Tools 30
  •    NLP Tools 105
  •    Linguistic Resources 215

Search Results | Total Results found :   1058

You refine search by : All Results
  Catalogue
In this paper, we attempt voice biometrics problem using only humming signal rather than normal speech. This paper adapts a new feature extraction technique which exploits Variable length Teager Energy Operator (VTEO) onto subband filtered signal of Mel filterbank. This feature modifies structure of state-of-the-art feature set, viz., Mel Frequency Cepstral Coefficients (MFCC). In particular, a new energy measure, viz., VTEO is employed to compute subband energies of different time-domain subband signals. The features derived MFCCs to capture magnitude and phase spectrum information via VTEO are termed as MFCC-VTMP. Discriminativelytrained polynomial classifier of 2nd order approximations is used as the basis for all experiments. MFCC-VTMP feature set is found to be better than MFCC for various evaluation factors such as order of polynomial classifier, dimension of feature vector, signal degradation conditions and class separability. % EER of MFCC and MFCC-VTMP are found to be 12.20 % and 12.01 %, respectively using 2nd order polynomial classification.
Index Terms: Humming, person recognition, Melcepstrum, VTEO, MFCC-VTMP

Added on October 28, 2016

17

  More Details
  • Contributed by : Consortium
  • Product Type : Research Paper
  • License Type : Freeware
  • System Requirement : Not Applicable
  • Author : Maulik C. Madhavi

Landmarks are the time instants in a speech signal which marks important events (such as vowels, consonants and glides) in the speech signal. This paper proposes use of novel vowel landmark detection (VLD) algorithm for low resourced language, viz., Gujarati, an Indian language. The proposed VLD method uses speech source information to detect the vowel landmarks which are points of high sonority. The excitation peaks in Hilbert envelope of Teager energy profile of zero frequency filtered (ZFF) speech signal can be interpreted as perceptually significant feature which contribute to the loudness. The performance of proposed VLD method is compared with existing loudness-based method. The results are reported on speech recorded in three different modes, viz., read, spontaneous and lecture followed by manual phonetic transcription by the transcribers (to be used as the ground truth) for Gujarati. In particular, the proposed VLD algorithm performs relatively better than an existing loudness-based method. The proposed VLD algorithm has detection rate of 78.92 %, 76.40 % and 73.89 %, which is 8.79 %, 7.23 % and 7.17 % more as compared to loudness-based method in lecture, spontaneous and read mode, respectively. The proposed algorithm is also shown to be robust against signal degradations such as white noise. In addition, proposed algorithm is fast and requires no training.
Index Terms: Landmark, vowel-nucleus, sonority, zerofrequency resonator (ZFR), Teager energy operator (TEO), loudness.

Added on October 28, 2016

5

  More Details
  • Contributed by : Consortium
  • Product Type : Research Paper
  • License Type : Freeware
  • System Requirement : Not Applicable
  • Author : Ankur G. Undhad

This is a Handwritten Recognition based keyboard application. This application allows smart writing of characters, words, and sentences using one’s writing style and then the algorithms will recognize the handwriting and convert into editable Text. The application has the option to insert recognized text into notepad, browsers or any editors for further use. It has built in keyboard to correct the recognized output (if wrongly recognized). There are multiple options of pen color to select from. User can erase, undo, redo, cut, copy and paste the handwriting in handwritten area. This Panel can be used with any windows tablet application provided the Windows Tablet supports Indian Languages (Unicode).
Smart Input Panel (SIP) using Handwriting Recognition Technology (Telugu)

System Requirement :
1) Operating System(OS) : Windows 7, 8, 8.1 (32-bit/64-Bit), 10 (64-Bit)
2) RAM memory : minimum 256MB free
3) Hard Disk Space: minimum 1GB free
4) Windows Tablet-PC with stylus

Added on October 25, 2016

101

  More Details
  • Contributed by : OHWR Consortium
  • Product Type : General Tools
  • License Type : Freeware
  • System Requirement : Windows

This is a Handwritten Recognition based keyboard application. This application allows smart writing of characters, words, and sentences using one’s writing style and then the algorithms will recognize the Handwriting and convert into editable Text. The application has the option to insert recognized text into notepad, browsers or any editors for further use. It has built in keyboard to correct the recognized output (if wrongly recognized). There are multiple options of pen color to select from. User can erase, undo, redo, cut, copy and paste the handwriting in handwritten area. This Panel can be used with any windows tablet application provided the Windows Tablet supports Indian Languages (Unicode).
Smart Input Panel (SIP) using Handwriting Recognition Technology (Punjabi)

System Requirement :
1) Operating System(OS) : Windows 7, 8, 8.1 (32-bit/64-Bit), 10 (64-Bit)
2) RAM memory : minimum 256MB free
3) Hard Disk Space: minimum 1GB free
4) Windows Tablet-PC with stylus

Last updated on December 20, 2016

18

  More Details
  • Contributed by : OHWR Consortium
  • Product Type : General Tools
  • License Type : Freeware
  • System Requirement : Windows

English-Gujarati Parallel Tourism Text corpus is developed in Unicode under English to Indian Language Machine Translation (EILMT) consortium. The core vocabulary of this corpus consist of various names, destinations, visiting places, vocabularies from art & architecture, culture and civilization. By and large, the corpus contains basically descriptions and information pertaining to tourist destinations and related matters of tourist interests. This corpus is created in excel format and size of the corpus is 11962 sentences.

Added on October 24, 2016

1
5

  More Details
  • Contributed by : EILMT Consortia, CDACPune
  • Product Type : Text Corpora
  • License Type : Research
  • System Requirement : Not Applicable