Bob 2.0 computation of spectrogram for audio samples. The silent tail/head are trimmed.
Algorithms have at least one input and one output. All algorithm endpoints are organized in groups. Groups are used by the platform to indicate which inputs and outputs are synchronized together. The first group is automatically synchronized with the channel defined by the block in which the algorithm is deployed.
Parameters allow users to change the configuration of an algorithm when scheduling an experiment
|Apply Mel-scale filtering or use linear (default - linear)
|Pre-emphasis coefficient, used in the spectrogram computation
|The length of the overlap between neighboring windows. Typically the half of window length.
|The length of the sliding processing window, typically about 20 ms
|Sampling rate of the speech signal
|The number of filter bands used in spectrogram computation
The code for this algorithm in Python
The ruler at 80 columns indicate suggested POSIX line breaks (for readability).
The editor will automatically enlarge to accomodate the entirety of your input
Use keyboard shortcuts for search/replace and faster editing. For example, use Ctrl-F (PC) or Cmd-F (Mac) to search through this box
Returns trimmed-spectrogram of an audio sample. Silent start and end of a sample are trimmed using Voice Activity Detection (VAD) labels as input.
This table shows the number of times this algorithm has been successfully run using the given environment. Note this does not provide sufficient information to evaluate if the algorithm will run when submitted to different conditions.