How to get volume level in current sample? Delphi 7

Question

On Delphi 7 I am running this code with NewAC Audio library. I am having short wav file, 44.100 kHz, mono, 16 bit.

unit Main;

interface

uses Windows, Messages, SysUtils, Variants, Classes, Graphics, Controls, Forms, Dialogs, ACS_Classes, ACS_DXAudio, ACS_Wave, ACS_Misc, ACS_Types, StdCtrls;

type
  TForm1 = class(TForm)
    AudioProcessor1: TAudioProcessor;
    WaveIn1: TWaveIn;
    DXAudioOut1: TDXAudioOut;
    OpenDialog1: TOpenDialog;
    Button1: TButton;
    Button2: TButton;
    procedure AudioProcessor1GetData(
      Sender: TComponent;
      var Buffer: Pointer;
      var NBlockBytes: Cardinal);
    procedure Button1Click(Sender: TObject);
    procedure Button2Click(Sender: TObject);
    procedure DXAudioOut1Done(Sender: TComponent);
    procedure AudioProcessor1Init(Sender: TComponent; var TotalSize: Int64);
    procedure AudioProcessor1Flush(Sender: TComponent);
  end;

var Form1: TForm1;
implementation
{$R *.dfm}

procedure TForm1.AudioProcessor1GetData(Sender: TComponent;
  var Buffer: Pointer; var NBlockBytes: Cardinal);
var Tmp : Integer;
 i : Integer;
 list1: TStringList;
 list2: TStringList;
 b1, b2, b3, b4:byte;
 si1, si2, si3, si4: ShortInt;
 mono: Boolean;
 values: array of word;
begin
  list1 := TStringList.Create;
  list2 := TStringList.Create;
  AudioProcessor1.Input.GetData(Buffer, NBlockBytes);
  if Buffer = nil then
    Exit;
  mono := false;
  case AudioProcessor1.Input.BitsPerSample of
    16 :
    begin
      B16 := Buffer;
      setlength(values, NBlockBytes div 2);
      for i := 0 to (NBlockBytes div 4) - 1 do
      begin
        Tmp := B16[i*2];
        move(B16[i*2], b1, 1); // copy left channel
        move(B16[i*2+1], b2, 1); // copy right channel
        move(B16[i*2+2], b3, 1); // copy left channel
        move(B16[i*2+3], b4, 1); // copy right channel
        si1 := b1;
        si2 := b2;
        si3 := b3;
        si4 := b4;
        list1.add(''+inttostr(si1));
        list2.add(''+inttostr(si2));
        list1.add(''+inttostr(si3));
        list2.add(''+inttostr(si4));
        B16[i*2] := B16[i*2 + 1];
        B16[i*2 + 1] := Tmp;
      end;
    end;
  end;
list1.free;
list2.free;

end;

procedure TForm1.AudioProcessor1Init(Sender: TComponent; var TotalSize: Int64);
begin
  TAudioProcessor(Sender).Input.Init;
  TotalSize := TAudioProcessor(Sender).Input.Size
end;

procedure TForm1.AudioProcessor1Flush(Sender: TComponent);
begin
  TAudioProcessor(Sender).Input.Flush;
end;


procedure TForm1.Button1Click(Sender: TObject);
begin
  if OpenDialog1.Execute then
  begin
    Button1.Enabled := False;
    WaveIn1.FileName := OpenDialog1.FileName;
    DXAudioOut1.Run;
  end;
end;

procedure TForm1.Button2Click(Sender: TObject);
begin
  DXAudioOut1.Stop;
end;    

procedure TForm1.DXAudioOut1Done(Sender: TComponent);
begin
  Button1.Enabled := True;
end;

end.

When I open the file in editing software I can see the amplitude of the sound and I see that the beginning values are 0. But when I run this program and I add the si1, si2, si3 and si4 to watch (in this order are the variables in watch), so I have these values in first iteration:

80,124,104,32.

I expected that these values should be 0 because there is silence on the begin.

First, may you explain why these are not zero?

Second, I am not sure what these values really represent. I know that si1 and si2 are first sample. But is it really level of the volume? How to correct the program to recognize the silence in the begin?

Tested file -> the section which should be passed to the function as first.

This part is not proccessed (because I processed only few cicles of the first loop):

I did some tests with file "silence plus", amplifications and see the first 8 cicles values.

Another test with word instead byte:

B16 := Buffer;
...
move(B16[i*2], w1, 2);
move(B16[i*2+1], w2, 2);

It really looks like the bits need to swap. I thought that in Windows XP I have little endian bit order. So I will write a swapper.

the audio contents of wav files are PCM encoded. Since you have 16 bits per sample in your case, the highest bits represent to top of the waveform and the lowest bits the bottom, so silence is at the middle (so it is not 0) — whosrdaddy
You have to be aware that there 50+ possible formats out there so the bytes themselves mean nothing without looking at the header. Anyway your code is not correct, the file you specify is 16bit mono,this means that you need to read 2 bytes per sample (and no left or right channel and ditch the shortints) and you need to swap them because wav data is stored in little endian format. Do some more reading — whosrdaddy

Johny Bony Johny Bony · Accepted Answer · 2019-11-07T15:48:52

The main problems of my code were:

1) Reading 1 byte of sample instead 2 bytes of sample.

2) The sample is signed, not unsigned. So when I tried to read two bytes of word, I get wrong numbers (see the last table in question).

3) I also tried to use two bytes of SmallInt swapped, but that resulted to crazy numbers like -25345, -1281, 26624, -19968 ... This is because on my system I use Little endian (Windows XP). There is not need to swap it on Windows.

So the solution was to copy 16 bits to SmallInt, no swap.

unit Main;

interface

uses
  Windows, Messages, SysUtils, Variants, Classes, Graphics, Controls, Forms,
  Dialogs, ACS_Classes, ACS_DXAudio, ACS_Wave, ACS_Misc, ACS_Types, StdCtrls;

type
  TForm1 = class(TForm)
    AudioProcessor1: TAudioProcessor;
    WaveIn1: TWaveIn;
    DXAudioOut1: TDXAudioOut;
    OpenDialog1: TOpenDialog;
    Button1: TButton;
    Button2: TButton;
    procedure AudioProcessor1GetData(
      Sender: TComponent;
      var Buffer: Pointer;
      var NBlockBytes: Cardinal);
    procedure Button1Click(Sender: TObject);
    procedure Button2Click(Sender: TObject);
    procedure DXAudioOut1Done(Sender: TComponent);
    procedure AudioProcessor1Init(Sender: TComponent; var TotalSize: Int64);
    procedure AudioProcessor1Flush(Sender: TComponent);
  private
    { Private declarations }
  public
    { Public declarations }
  end;

var  Form1: TForm1;
implementation
{$R *.dfm}
procedure TForm1.AudioProcessor1GetData(Sender: TComponent;
   var Buffer: Pointer; var NBlockBytes: Cardinal);
var
 B16 : PBuffer16;
 i, end_  : Integer;
 si1, si2: SmallInt;
begin
  AudioProcessor1.Input.GetData(Buffer, NBlockBytes);
  if Buffer = nil then
    Exit;
  case AudioProcessor1.Input.BitsPerSample of
    16 :
    begin
      B16 := Buffer;
      end_ := (NBlockBytes div 2) - 1;
      for i := 0 to end_ do
      begin
        move(B16[i*2], si1, 2);
        move(B16[i*2+1], si2, 2);
      end;
    end;
  end;
end;

procedure TForm1.AudioProcessor1Init(Sender: TComponent; var TotalSize: Int64);
begin
  TAudioProcessor(Sender).Input.Init;
  TotalSize := TAudioProcessor(Sender).Input.Size
end;    

procedure TForm1.AudioProcessor1Flush(Sender: TComponent);
begin
  TAudioProcessor(Sender).Input.Flush;
end;


procedure TForm1.Button1Click(Sender: TObject);
begin
  if OpenDialog1.Execute then
  begin
    Button1.Enabled := False;
    WaveIn1.FileName := OpenDialog1.FileName;
    DXAudioOut1.Run;
  end;
end;

procedure TForm1.Button2Click(Sender: TObject);
begin
  DXAudioOut1.Stop;
end;

procedure TForm1.DXAudioOut1Done(Sender: TComponent);
begin
  Button1.Enabled := True;
end;

end.

Here are the values:

How to get volume level in current sample? Delphi 7

1 Answers