The SpeechMark Command Line Utility, Mac Edition

The SpeechMark family of products detects and measures acoustic landmarks —acoustic events that correlate with changes in speech articulation. Landmarks are useful for investigating non-lexical attributes of speech, such as differences in production of the same speech material by the same speaker under different conditions.

The SpeechMark Command Line Utility, Mac Edition is a version of the SpeechMark technology that is callable from an OS X terminal window. The utility is a command line program named spmark, which processes a wave file containing recorded speech, detects acoustic landmarks in the recorded speech, and outputs a text-format “landmark file” with information about the detected landmarks.

The text output of the SpeechMark Command Line Utility can be imported into other programs. This utility is well-suited for batch processing, as no user interaction is required when the program is running. The Utility is designed to be easily integrated by the end user into most third-party speech processing systems.

The SpeechMark Command Line Utility is primarily suited to the following uses:

  • Processing large amount of audio, and/or many audio files, in “batch mode”;
  • Adding landmark detection capabilities to any speech analysis system that is not directly supported by other SpeechMark products.

 

Features

The SpeechMark Command Line Utility:

  • Analyzes a speech file in order to detect and identify the location of acoustic landmarks (See How are Acoustic Landmarks Detected?)
    • All SpeechMark products generate a landmark file (“.lm”), which is a text file that contains one line of information for each generated landmark. That line contains a timestamp, the label of the landmark, and a numerical “strength” value;
      An example of the first few lines from a .lm file is shown below.

 

Examples

The following figure shows two invocations of spmark:

  1. The first invocation shows how the “-h” option is used to print help describing the program’s command line syntax;
  2. The second invocation highlights the specification of one input filename as a required argument on the command line. The specified file is the .WAV file that contains the speech in which landmarks are to be found.

 

System Requirements

  • OS X (Lion or Mountain Lion version);
  • the MATLAB Compiler Runtime (MCR) object. This third-party software is installed automatically during the SpeechMark installation process if it is not already present on the user’s system and runnable.

 

Downloads

  • Click here to download this SpeechMark product.

LMFile

Figure 1: The header and first six data lines of a SpeechMark “.lm” file. Among other information, the header includes the name and version number of the landmark product that generated the file; and the identifier of the waveform that was processed. Each data line includes a timestamp, a landmark type code, and a “strength” value.

Figure 2: The first call to spmark shows the /? help option. The second call to spmark shows an example in which spx2.wav is the input speech file and the /g option indicates that the speaker is an adult female.CmdLine-h

The SpeechMark Command Line Utility, Windows Edition

The SpeechMark family of products detects and measures acoustic landmarks —acoustic events that correlate with changes in speech articulation. Landmarks are useful for investigating non-lexical attributes of speech, such as differences in production of the same speech material by the same speaker under different conditions.

The SpeechMark Command Line Utility, Windows Edition is a version of the SpeechMark technology that is callable from a Windows command window. The utility is a command line program named spmark.exe, which processes a wave file containing recorded speech, detects acoustic landmarks in the recorded speech, and outputs a text-format “landmark file” with information about the detected landmarks.

CmdLine2Features

The text output of the SpeechMark Command Line Utility can be imported into other programs. This utility is well-suited for batch processing, as no user interaction is required when the program is running. The Utility is designed to be easily integrated by the end user into most third-party speech processing systems.

The SpeechMark Command Line Utility is primarily suited to the following uses:

 

    • All SpeechMark products generate a landmark file (“.lm”), which is a text file that contains one line of information for each generated landmark. That line contains a timestamp, the label of the landmark, and a numerical “strength” value; An example of the first few lines from a .lm file is shown below.

 

Examples

CmdLineThe following figure shows two invocations of spmark.exe:

  1. The first invocation shows how the “/?” option is used to print help describing the program’s command line syntax;
  2. The second invocation highlights the specification of one input filename as a required argument on the command line. The specified file is the .WAV file that contains the speech in which landmarks are to be found.

 

System Requirements

  • Windows XP or Windows 7;
  • The MATLAB Compiler Runtime (MCR) object. This third-party software is installed automatically if it is not found on the user’s system by the SpeechMark installation process.

Downloads Click here to download this SpeechMark product.

 

SpeechMark R Package, Windows Edition

The SpeechMark R Package is now unsupported, and its use is deprecated. However, we invite anyone who is seriously interested in this Package to communicate with us and discuss their interest and needs.

The SpeechMark family of products detects and measures acoustic landmarks —acoustic events that correlate with changes in speech articulation. Landmarks are useful for investigating non-lexical attributes of speech, such as differences in production of the same speech material by the same speaker under different conditions.

The SpeechMark R Package for Windows adds landmark support to the R software environment for statistical computing and graphics.

RPackage1Features

The R Package:

    • Analyzes speech files to detect and identify the location of acoustic landmarks
    • Displays the location of acoustic landmarks.
      • Landmark labels are superimposed on the audio signal waveform.

 

    • Computes a Vowel Space Plot for detected vowel landmarks.
      • In the Vowel Space Plot, SpeechMark plots the (F1, F2) positions of detected vowel landmarks.

 

      • In addition, as a visual guide, SpeechMark also draws a polygon (dashed blue line) showing the approximate range of the adult vowel space. That is, the polygon shows accepted values of the adult vowel space, (not boundaries derived from the vowels being plotted).

RPackage2

    • Calculates the number of syllables, the number of utterances and the number of landmarks in syllables and utterances.
    • Saves and Loads landmarks data to disk.

 

System Requirements

  • Windows XP or Windows 7
  • The latest release of R Software Environment.
  • The MATLAB Compiler Runtime object.

 

Downloads

  • Click here to download this SpeechMark product.

SpeechMark WaveSurfer Plug-in, Mac Edition

The SpeechMark family of products detects and measures acoustic landmarks —acoustic events that correlate with changes in speech articulation. Landmarks are useful for investigating non-lexical attributes of speech, such as differences in production of the same speech material by the same speaker under different conditions.

The SpeechMark WaveSurfer Plug-in, Mac Edition adds landmark support to the WaveSurfer speech analysis package.

Features

The SpeechMark Plug-in:

    • Analyzes speech files to detect and identify the location of acoustic landmarks
    • Displays the location of acoustic landmarks on a pane within WaveSurfer
      • Landmark labels are superimposed on the audio signal waveform

WSPlug-in 1

    • Displays power contours in selected frequency bands that are used to identify acoustic landmarks

WSPlug-in 3

    • Supports user preferences for landmark configuration
      • As shown in Figure 3, the set of landmarks to be displayed and output can be modified by the user

WSPlug-in 4

    • Generates output files which specify the location (time) and type of the detected landmarks
      • All versions of SpeechMark generate a landmark file (“.lm” file—see Figure 4). A landmark files is a text file that contains one line of information for each generated landmark. That line contains a timestamp, the label of the landmark, and a numerical “strength” value;

WSPlug-in 2

      • The SpeechMark Plug-in also generates a WaveSurfer “lab.lab” file which represents acoustic landmarks as standard WaveSurfer labels. The user can open this landmark label file in WaveSurfer to use these landmarks as standard WaveSurfer transcription labels.

 

    • WSPlug-in 5Computes a Vowel Space Plot for detected vowel landmarks
      • In the Vowel Space Plot, SpeechMark plots the (F1, F2) positions of detected vowel landmarks.
      • Vowels with unusually high formant bandwidth are plotted in green, the rest are plotted in red.
      • In addition, as a visual guide, SpeechMark also draws a polygon (dashed blue line) showing the approximate range of the adult vowel space. That is, the polygon shows accepted values of the adult vowel space, (not boundaries derived from the vowels being plotted).

 

 

System Requirements

  • Mac OS X (Lion or Mountain Lion version);
  • The latest release of WaveSurfer that can be downloaded
    from the sourceforge.net web site (currently version 1.8.8p4) or WaveSurfer 1.8.5;
  • The MATLAB Compiler Runtime object (which is normally downloaded and installed automatically as part of the SpeechMark product installation process).

 

Downloads

  • Click here to download this SpeechMark product.

SpeechMark WaveSurfer Plug-in, Windows Edition

WaveSurferPlugin1The SpeechMark family of products detects and measures acoustic landmarks —acoustic events that correlate with changes in speech articulation. Landmarks are useful for investigating non-lexical attributes of speech, such as differences in production of the same speech material by the same speaker under different conditions.

The SpeechMark WaveSurfer Plug-in for Windows adds landmark support to the WaveSurfer speech analysis package.

Features

The SpeechMark Plug-in:

    • Analyzes speech files to detect and identify the location of acoustic landmarks
    • Displays the location of acoustic landmarks on a pane within WaveSurfer
      • Landmark labels are superimposed on the audio signal waveform.

 

    • Displays power contours in selected frequency bands that are used to identify acoustic landmarksWaveSurferPlugin2

 

    • Supports user preferences for landmark configuration
      • As shown in Figure 3, the set of landmarks to be displayed and output can be modified by the user.

WaveSurferPlugin3

    • Generates output files which specify the location (time) and type of the detected landmarks
      • All versions of SpeechMark generate a landmark file (“.lm” file—see Figure 4). A landmark files is a text file that contains one line of information for each generated landmark. That line contains a timestamp, the label of the landmark, and a numerical “strength” value;

WaveSurferPlugin4

      • The SpeechMark Plug-in also generates a WaveSurfer “lab.lab” file which represents acoustic landmarks as standard WaveSurfer labels. The user can open this landmark label file in WaveSurfer to use these landmarks as standard WaveSurfer transcription labels.

 

    • WaveSurferPlugin5Computes a Vowel Space Plot for detected vowel landmarks
      • In the Vowel Space Plot, SpeechMark plots the (F1, F2) positions of detected vowel landmarks.
      • Vowels with unusually high formant bandwidth are plotted in green, the rest are plotted in red.
      • In addition, as a visual guide, SpeechMark also draws a polygon (dashed blue line) showing the approximate range of the adult vowel space. That is, the polygon shows accepted values of the adult vowel space, (not boundaries derived from the vowels being plotted).

 

System Requirements

  • Windows XP or Windows 7
  • The latest release of WaveSurfer that can be downloaded from the
    sourceforge.net web site (currently version 1.8.8p4) or WaveSurfer 1.8.5
  • The MATLAB Compiler Runtime object (which is normally downloaded
    and installed automatically as part of the SpeechMark product installation process).

 

Downloads

  • Click here to download this SpeechMark product.

The SpeechMark MATLAB Toolbox

The SpeechMark family of products detects and measures acoustic landmarks —acoustic events that correlate with changes in speech articulation. Landmarks are useful for investigating non-lexical attributes of speech, such as differences in production of the same speech material by the same speaker under different conditions.

The SpeechMark MATLAB Toolbox Product adds acoustic landmark support to the MATLAB omputational environment. It comes complete with comprehensively documented code, sample data files, and demo scripts.

Features

The SpeechMark Toolbox:

  • Computation of pitch tracks, “cepstrograms,” and band energy envelopes within speech signals;
  • Automatic detection of both abrupt and maximal acoustic landmarks in speech;
  • Post-processing of generated landmark sequences into a “syllable” structure which reveals something about the complexity of the utterances in the source, including voiced regions (within which pitch measurements are meaningful), and certain “pseudo-speech” regions which can be classified as non-speech noise.
  • Generation of landmark-related plots and images;
  • Generation of a standard MATLAB .mat (binary) file containing information about detected landmarks, amplitude envelope, and other signal contours and attributes;
  • Generation of a standard SpeechMark “.lm” file containing information about detected landmarks;
  • Tools for processing real time audio streams and generating acoustic landmarks in real time;
  • Comprehensive toolbox documentation compatible with the MATLAB Supplemental Software browser, including a roadmap page, example scripts and output files, and function pages;
  • Invocation of the MATLAB Imaging Toolbox, when available, to speed up computations.

 

System Requirements:

  • One of the following operating systems: Windows 7, Windows XP, Apple OSX (Lion or Mountain Lion);
  • An installed copy of MATLAB (version R2010b or newer);
  • An installed copy of the MATLAB Signal Processing Toolbox.

 

Potential Enhancements:

  • A GUI-based demo, so that the end user can quickly get a feel for the various parameters and how they affect the processing/result;
  • A user control that will allow a user to specify features of the landmarks-in-waveform plot to be included or removed.

Screen Shots to be displayed in Product documentation:

  • Landmarks-in-waveform plot;
  • Vowel space plot.

 

Downloads

  • Click here to download this SpeechMark product.