Error using fread Invalid file identifier in Microsoft MSR ToolKit

I am getting the following error while using Microsoft MSR ToolBox

   Error using fread
   Invalid file identifier. Use fopen to generate a valid file identifier.

   Error in htkread (line 8)
   nframes = fread(fid, 1, 'int32'); % number of frames

   Error in DebugCode (line 13)
   data{ix} = htkread(filenames{ix});

The code of functions where the errors arise are:

function gmm = mapAdapt(dataList, ubmFilename, tau, config, gmmFilename)
......
.

if ischar(dataList) || iscellstr(dataList),
  dataList = load_data(dataList);
end
if ~iscell(dataList),
  error('Oops! dataList should be a cell array!');
end
nfiles = length(dataList);
.
..
.......
end

*****************************************************************************

function data = load_data(datalist)
% load all data into memory
if ~iscellstr(datalist)
    fid = fopen(datalist, 'rt');
    filenames = textscan(fid, '%s');
    fclose(fid);
    filenames = filenames{1};
else
    filenames = datalist;
end
nfiles = size(filenames, 1);
data = cell(nfiles, 1);
for ix = 1 : nfiles,
    data{ix} = htkread(filenames{ix});
end

**************************************************************************************

    function [data, frate, feakind] = htkread(filename)
    % reads features with HTK format
    %
    % Omid Sadjadi <[e-mail]>
    % Microsoft Research, Conversational Systems Research Center

    fid = fopen(filename, 'rb', 'ieee-be');
    nframes = fread(fid, 1, 'int32'); % number of frames %%ERROR
    frate   = fread(fid, 1, 'int32'); % frame rate in 100 nano-seconds unit
    nbytes  = fread(fid, 1, 'short'); % number of bytes per feature value
    feakind = fread(fid, 1, 'short'); % 9 is USER
    ndim = nbytes / 4; % feature dimension (4 bytes per value)
    data = fread(fid, [ndim, nframes], 'float');
    fclose(fid);

datalist.txt is a file with 6300 entries like

htkfiles\fadg0_si1279.htk
htkfiles\fadg0_si1909.htk
htkfiles\fadg0_si649.htk
htkfiles\fadg0_sx109.htk
htkfiles\fadg0_sx19.htk
htkfiles\fadg0_sx199.htk
htkfiles\fadg0_sx289.htk
htkfiles\fadg0_sx379.htk
htkfiles\faem0_sa1.htk
htkfiles\faem0_sa2.htk
htkfiles\faem0_si1392.htk
htkfiles\faem0_si2022.htk
htkfiles\faem0_si762.htk
htkfiles\faem0_sx132.htk
htkfiles\faem0_sx222.htk
htkfiles\faem0_sx312.htk
htkfiles\faem0_sx402.htk
htkfiles\faem0_sx42.htk
htkfiles\fajw0_sa1.htk
htkfiles\fajw0_sa2.htk
htkfiles\fajw0_si1263.htk
htkfiles\fajw0_si1893.htk

Answer 1

[Walter Roberson]

One or more of the files named in that list do not exist relative to your current directory.

The code

      fid = fopen(filename, 'rb', 'ieee-be');

would be better as

      [fid, message] = fopen(filename, 'rb', 'ieee-be');
      if fid < 0
        error('Failed to open file "%s" because "%s", filename, message);
      end

[Sonal Joshi]

Thank you. It helped

[Vinay H]

How did you get dataList. I downloaded from https://www.microsoft.com/en-us/download/details.aspx?id=52279 and it does not have database to train. Please let me know how you got database.

[Sonal Joshi]

Its a bit late, but in case you are still stuck, here is the answer. You will need to prepare the dataList according to your data. The format is:

path_to_features\speaker1_utterance1.htk
path_to_features\speaker2_utterance2.htk
.
.

The one I have put above is for TIMIT database ( https://catalog.ldc.upenn.edu/ldc93s1 ) which is a paid database that can be purchased from LDC.