Submit a comment to an "Available C++ Libraries FAQ" entry

CategoryLibraries available to download (Q-Z)

SV_Lib - Class library for speech recognition and speaker verification

The following highlights the main features of this library:

1. Modeling
   • Continuous density HMM,
   • Discrete density HMM,
   • Gaussian Mixture Model (GMM),
   • Vector Quantization model (VQ),
   • Multivariate Gaussian model,
   • Dynamic Time Wrapping (DTW),
2. Feature extraction
   • Mel-scaled FFT based cepstrum (MFCC),
   • LPC based cepstrum (LPCC),
   • Dynamic features (delta cepstrum),
   • Pitch extractor,
3. Speech Input
   • Read raw speech data (16-bit PCM, 8-bit ULAW),
   • Read data with SPHERE header (NIST format) (both compressed and uncompressed),
4. Auxiliary Classes
   • Fourier transforms (FFT/IFFT),
   • Discrete cosine transform (DCT/IDCT),
   • LPC analysis,
   • Design FIR filter (lowpass, highpass, bandpass, bandstop),
   • Matrix (Inverse, Determinant, Eigen, SVD),
   • Waveform generator (noise, modulated tone, sawtooth etc.),
   • Window functions (hamming, hanning, triangle, blackman, etc.)
   • Function operation (root, minimum, numerical integration).

Licensing : Freeware

Do not expect an immediate response - the contents of this form will be added to a queue, which I process manually about once a week. If you don't fill in your email address correctly, you will not (obviously) get any reply at all. Other invalid information may result in a mailed request for clarification.

Enter your comment in the areas provided below. Be sure to include your name and email address.

Please don't bother trying to post spam or links to dodgy web sites - everything you post here is reviewed by a human being before being released for public viewing.

For more information on any of Trumphurst's products and services, please

• Contact us using our contact form
• Phone us at +44 1691 659510 (In the U.K., replace "+44" with "0". Elsewhere, replace "+" with your international dialling code.)