我正在开发一个新的UWP应用，该应用应该监视声音并为每次突然的声音击打（枪声或拍手声）触发事件。
无需保存音频 我尝试实施this
SoundMonitoringPage ：
public sealed partial class MyPage : Page
{
private async void Page_Loaded(object sender, RoutedEventArgs e)
{
string deviceId = Windows.Media.Devices.MediaDevice.GetDefaultAudioCaptureId(Windows.Media.Devices.AudioDeviceRole.Communications);
gameChatAudioStateMonitor = AudioStateMonitor.CreateForCaptureMonitoringWithCategoryAndDeviceId(MediaCategory.GameChat, deviceId);
gameChatAudioStateMonitor.SoundLevelChanged += GameChatSoundLevelChanged;
//other logic
}
}
声级更改：
private void GameChatSoundLevelChanged(AudioStateMonitor sender, object args)
{
switch (sender.SoundLevel)
{
case SoundLevel.Full:
LevelChangeEvent();
break;
case SoundLevel.Muted:
LevelChangeEvent();
break;
case SoundLevel.Low:
// Audio capture should never be "ducked", only muted or full volume.
Debug.WriteLine("Unexpected audio state change.");
break;
}
}
ENV：Windows 10（v1809）IDE：VS 2017
不确定这是否是正确的方法。这不会启用音频，也不会触发电平更改事件。
我在WinForms＆NAudio教程here中看到了其他选项。可能使用采样频率，我可以检查事件...没有必须将NAudio与UWP一起使用的教程，以绘制图形并确定频率。
更新：
@Rob Caplan的建议-MSFT，这就是我的最终目的
IMemoryBufferByteAccess.cs
// We are initializing a COM interface for use within the namespace
// This interface allows access to memory at the byte level which we need to populate audio data that is generated
[ComImport]
[Guid("5B0D3235-4DBA-4D44-865E-8F1D0E4FD04D")]
[InterfaceType(ComInterfaceType.InterfaceIsIUnknown)]
unsafe interface IMemoryBufferByteAccess
{
void GetBuffer(out byte* buffer, out uint capacity);
}
GunFireMonitorPage.xaml.cs
public sealed partial class GunFireMonitorPage : Page
{
private MainPage _rootPage;
public static GunFireMonitorPage Current;
private AudioGraph _graph;
private AudioDeviceOutputNode _deviceOutputNode;
private AudioFrameInputNode _frameInputNode;
public double Theta;
public DrivePage()
{
InitializeComponent();
Current = this;
}
protected override async void OnNavigatedTo(NavigationEventArgs e)
{
_rootPage = MainPage.Current;
await CreateAudioGraph();
}
protected override void OnNavigatedFrom(NavigationEventArgs e)
{
_graph?.Dispose();
}
private void Page_Loaded(object sender, RoutedEventArgs e)
{
}
private unsafe AudioFrame GenerateAudioData(uint samples)
{
// Buffer size is (number of samples) * (size of each sample)
// We choose to generate single channel (mono) audio. For multi-channel, multiply by number of channels
uint bufferSize = samples * sizeof(float);
AudioFrame audioFrame = new AudioFrame(bufferSize);
using (AudioBuffer buffer = audioFrame.LockBuffer(AudioBufferAccessMode.Write))
using (IMemoryBufferReference reference = buffer.CreateReference())
{
// Get the buffer from the AudioFrame
// ReSharper disable once SuspiciousTypeConversion.Global
// ReSharper disable once UnusedVariable
((IMemoryBufferByteAccess) reference).GetBuffer(out var dataInBytes, out var capacityInBytes);
// Cast to float since the data we are generating is float
var dataInFloat = (float*)dataInBytes;
float freq = 1000; // choosing to generate frequency of 1kHz
float amplitude = 0.3f;
int sampleRate = (int)_graph.EncodingProperties.SampleRate;
double sampleIncrement = (freq * (Math.PI * 2)) / sampleRate;
// Generate a 1kHz sine wave and populate the values in the memory buffer
for (int i = 0; i < samples; i++)
{
double sinValue = amplitude * Math.Sin(Theta);
dataInFloat[i] = (float)sinValue;
Theta += sampleIncrement;
}
}
return audioFrame;
}
private void node_QuantumStarted(AudioFrameInputNode sender, FrameInputNodeQuantumStartedEventArgs args)
{
// GenerateAudioData can provide PCM audio data by directly synthesizing it or reading from a file.
// Need to know how many samples are required. In this case, the node is running at the same rate as the rest of the graph
// For minimum latency, only provide the required amount of samples. Extra samples will introduce additional latency.
uint numSamplesNeeded = (uint)args.RequiredSamples;
if (numSamplesNeeded != 0)
{
AudioFrame audioData = GenerateAudioData(numSamplesNeeded);
_frameInputNode.AddFrame(audioData);
}
}
private void Button_Click(object sender, RoutedEventArgs e)
{
if (generateButton.Content != null && generateButton.Content.Equals("Generate Audio"))
{
_frameInputNode.Start();
generateButton.Content = "Stop";
audioPipe.Fill = new SolidColorBrush(Colors.Blue);
}
else if (generateButton.Content != null && generateButton.Content.Equals("Stop"))
{
_frameInputNode.Stop();
generateButton.Content = "Generate Audio";
audioPipe.Fill = new SolidColorBrush(Color.FromArgb(255, 49, 49, 49));
}
}
private async Task CreateAudioGraph()
{
// Create an AudioGraph with default settings
AudioGraphSettings settings = new AudioGraphSettings(AudioRenderCategory.Media);
CreateAudioGraphResult result = await AudioGraph.CreateAsync(settings);
if (result.Status != AudioGraphCreationStatus.Success)
{
// Cannot create graph
_rootPage.NotifyUser($"AudioGraph Creation Error because {result.Status.ToString()}", NotifyType.ErrorMessage);
return;
}
_graph = result.Graph;
// Create a device output node
CreateAudioDeviceOutputNodeResult deviceOutputNodeResult = await _graph.CreateDeviceOutputNodeAsync();
if (deviceOutputNodeResult.Status != AudioDeviceNodeCreationStatus.Success)
{
// Cannot create device output node
_rootPage.NotifyUser(
$"Audio Device Output unavailable because {deviceOutputNodeResult.Status.ToString()}", NotifyType.ErrorMessage);
speakerContainer.Background = new SolidColorBrush(Colors.Red);
}
_deviceOutputNode = deviceOutputNodeResult.DeviceOutputNode;
_rootPage.NotifyUser("Device Output Node successfully created", NotifyType.StatusMessage);
speakerContainer.Background = new SolidColorBrush(Colors.Green);
// Create the FrameInputNode at the same format as the graph, except explicitly set mono.
AudioEncodingProperties nodeEncodingProperties = _graph.EncodingProperties;
nodeEncodingProperties.ChannelCount = 1;
_frameInputNode = _graph.CreateFrameInputNode(nodeEncodingProperties);
_frameInputNode.AddOutgoingConnection(_deviceOutputNode);
frameContainer.Background = new SolidColorBrush(Colors.Green);
// Initialize the Frame Input Node in the stopped state
_frameInputNode.Stop();
// Hook up an event handler so we can start generating samples when needed
// This event is triggered when the node is required to provide data
_frameInputNode.QuantumStarted += node_QuantumStarted;
// Start the graph since we will only start/stop the frame input node
_graph.Start();
}
}
GunFireMonitorPage.xaml
<Page
x:Class="SmartPileInspector.xLite.GunFireMonitorPage"
xmlns="http://schemas.microsoft.com/winfx/2006/xaml/presentation"
xmlns:x="http://schemas.microsoft.com/winfx/2006/xaml"
xmlns:d="http://schemas.microsoft.com/expression/blend/2008"
xmlns:mc="http://schemas.openxmlformats.org/markup-compatibility/2006"
mc:Ignorable="d" Loaded="Page_Loaded"
HorizontalAlignment="Center"
Background="{ThemeResource ApplicationPageBackgroundThemeBrush}">
<ScrollViewer HorizontalAlignment="Center">
<StackPanel HorizontalAlignment="Center">
<!-- more page content -->
<Grid HorizontalAlignment="Center">
<Grid.ColumnDefinitions>
<ColumnDefinition Width="*"/>
<ColumnDefinition Width="*"/>
</Grid.ColumnDefinitions>
<Grid.RowDefinitions>
<RowDefinition Height="55"></RowDefinition>
</Grid.RowDefinitions>
</Grid>
<AppBarButton x:Name="generateButton" Content="Generate Audio" Click="Button_Click" MinWidth="120" MinHeight="45" Margin="0,50,0,0"/>
<Border x:Name="frameContainer" BorderThickness="0" Background="#4A4A4A" MinWidth="120" MinHeight="45" Margin="0,20,0,0">
<TextBlock x:Name="frame" Text="Frame Input" VerticalAlignment="Center" HorizontalAlignment="Center" />
</Border>
<StackPanel>
<Rectangle x:Name="audioPipe" Margin="0,20,0,0" Height="10" MinWidth="160" Fill="#313131" HorizontalAlignment="Stretch"/>
</StackPanel>
<Border x:Name="speakerContainer" BorderThickness="0" Background="#4A4A4A" MinWidth="120" MinHeight="45" Margin="0,20,0,0">
<TextBlock x:Name="speaker" Text="Output Device" VerticalAlignment="Center" HorizontalAlignment="Center" />
</Border>
<!--</AppBar>-->
</StackPanel>
</ScrollViewer>
</Page>
没有生成图形。并且有持续的蜂鸣声并带有蓝线。
更新：已实现AudioVisualizer
借助AudioVisualizer，我能够绘制虱子音频图。
AudioGraph _graph;
AudioDeviceInputNode _inputNode;
PlaybackSource _source;
SourceConverter _converter;
protected override void OnNavigatedTo(NavigationEventArgs e)
{
_rootPage = MainPage.Current;
_rootPage.SetDimensions(700, 600);
base.OnNavigatedTo(e);
CreateAudioGraphAsync();
}
protected override void OnNavigatedFrom(NavigationEventArgs e)
{
base.OnNavigatedFrom(e);
_graph?.Stop();
_graph?.Dispose();
_graph = null;
}
async void CreateAudioGraphAsync()
{
var graphResult = await AudioGraph.CreateAsync(new AudioGraphSettings(Windows.Media.Render.AudioRenderCategory.Media));
if (graphResult.Status != AudioGraphCreationStatus.Success)
throw new InvalidOperationException($"Graph creation failed {graphResult.Status}");
_graph = graphResult.Graph;
var inputNodeResult = await _graph.CreateDeviceInputNodeAsync(MediaCategory.Media);
if (inputNodeResult.Status == AudioDeviceNodeCreationStatus.Success)
{
_inputNode = inputNodeResult.DeviceInputNode;
_source = PlaybackSource.CreateFromAudioNode(_inputNode);
_converter = new SourceConverter
{
Source = _source.Source,
MinFrequency = 110.0f,
MaxFrequency = 3520.0f,
FrequencyCount = 12 * 5 * 5,
FrequencyScale = ScaleType.Linear,
SpectrumRiseTime = TimeSpan.FromMilliseconds(20),
SpectrumFallTime = TimeSpan.FromMilliseconds(200),
RmsRiseTime = TimeSpan.FromMilliseconds(20),
RmsFallTime = TimeSpan.FromMilliseconds(500),
ChannelCount = 1
};
// Note A2
// Note A7
// 5 octaves, 5 bars per note
// Use RMS to gate noise, fast rise slow fall
NotesSpectrum.Source = _converter;
_graph.Start();
}
else
{
_rootPage.NotifyUser("Cannot access microphone", NotifyType.ErrorMessage);
}
}
现在的挑战是，当波频率高于阈值时，如何连接事件？在那种情况下，我想计算拍摄数量，时间戳及其强度。
这是我的Recording of live sound，正如您在这里可以看到的那样，当有很大的锤击声（每秒钟或更短）时，我想打个电话。
答案 0 :(得分：3)
您可以通过找到该帧中所有pcm数据的平均幅度来找到该帧的分贝。我相信您希望创建一个处理输入的图形，如下所示
private static event LoudNoise<double>;
private static int quantum = 0;
static AudioGraph ingraph;
private static AudioDeviceInputNode deviceInputNode;
private static AudioFrameOutputNode frameOutputNode;
public static async Task<bool> CreateInputDeviceNode(string deviceId)
{
Console.WriteLine("Creating AudioGraphs");
// Create an AudioGraph with default settings
AudioGraphSettings graphsettings = new AudioGraphSettings(AudioRenderCategory.Media);
graphsettings.EncodingProperties = new AudioEncodingProperties();
graphsettings.EncodingProperties.Subtype = "Float";
graphsettings.EncodingProperties.SampleRate = 48000;
graphsettings.EncodingProperties.ChannelCount = 2;
graphsettings.EncodingProperties.BitsPerSample = 32;
graphsettings.EncodingProperties.Bitrate = 3072000;
//settings.DesiredSamplesPerQuantum = 960;
//settings.QuantumSizeSelectionMode = QuantumSizeSelectionMode.ClosestToDesired;
CreateAudioGraphResult graphresult = await AudioGraph.CreateAsync(graphsettings);
if (graphresult.Status != AudioGraphCreationStatus.Success)
{
// Cannot create graph
return false;
}
ingraph = graphresult.Graph;AudioGraphSettings nodesettings = new AudioGraphSettings(AudioRenderCategory.GameChat);
nodesettings.EncodingProperties = AudioEncodingProperties.CreatePcm(48000, 2, 32);
nodesettings.DesiredSamplesPerQuantum = 960;
nodesettings.QuantumSizeSelectionMode = QuantumSizeSelectionMode.ClosestToDesired;
frameOutputNode = ingraph.CreateFrameOutputNode(ingraph.EncodingProperties);
quantum = 0;
ingraph.QuantumStarted += Graph_QuantumStarted;
DeviceInformation selectedDevice;
string device = Windows.Media.Devices.MediaDevice.GetDefaultAudioCaptureId(Windows.Media.Devices.AudioDeviceRole.Default);
if (!string.IsNullOrEmpty(device))
{
selectedDevice = await DeviceInformation.CreateFromIdAsync(device);
} else
{
return false;
}
CreateAudioDeviceInputNodeResult result =
await ingraph.CreateDeviceInputNodeAsync(MediaCategory.Media, nodesettings.EncodingProperties, selectedDevice);
if (result.Status != AudioDeviceNodeCreationStatus.Success)
{
// Cannot create device output node
return false;
}
deviceInputNode = result.DeviceInputNode;
deviceInputNode.AddOutgoingConnection(frameOutputNode);
frameOutputNode.Start();
ingraph.Start();
return true;
}
private static void Graph_QuantumStarted(AudioGraph sender, object args)
{
if (++quantum % 2 == 0)
{
AudioFrame frame = frameOutputNode.GetFrame();
float[] dataInFloats;
using (AudioBuffer buffer = frame.LockBuffer(AudioBufferAccessMode.Write))
using (IMemoryBufferReference reference = buffer.CreateReference())
{
// Get the buffer from the AudioFrame
((IMemoryBufferByteAccess)reference).GetBuffer(out byte* dataInBytes, out uint capacityInBytes);
float* dataInFloat = (float*)dataInBytes;
dataInFloats = new float[capacityInBytes / sizeof(float)];
for (int i = 0; i < capacityInBytes / sizeof(float); i++)
{
dataInFloats[i] = dataInFloat[i];
}
}
double decibels = 0f;
foreach (var sample in dataInFloats)
{
decibels += Math.Abs(sample);
}
decibels = 20 * Math.Log10(decibels / dataInFloats.Length);
// You can pass the decibel value where ever you'd like from here
if (decibels > 10)
{
LoudNoise?.Invoke(this, decibels);
}
}
}
P.S。我做了所有这些静态操作，但是如果它们都在同一实例中，那自然就可以了
我也从我自己的项目中部分复制了此文件，因此其中有些部分我忘了修剪。希望对您有帮助
答案 1 :(得分：0)
回答“这是正确的方法”的问题：不，AudioStateMonitor不能解决问题。
AudioStateMonitor。SoundLevelChanged告诉您系统是否在回避声音，以免干扰其他声音。例如，它可以使音乐静音，从而有利于电话铃声。 SoundLevelChanged不会告诉您有关已录制声音的音量或频率的任何信息，这是检测手掌声所需要的。
正确的方法将遵循以下方法：使用AudioGraph（或WASAPI，但不是来自C＃）将原始音频捕获到AudioFrameOutputNode中以处理信号，然后通过FFT运行以检测声音在您的目标频率和音量上AudioCreation sample演示了如何使用AudioGraph，但没有专门针对AudioFrameOutputNode。
每https://home.howstuffworks.com/clapper1.htm拍手将在2200Hz到2800Hz的频率范围内。
识别枪声似乎要复杂得多，因为不同的枪具有不同的签名。快速搜索发现了有关此算法而不是琐碎算法的几篇研究论文。我怀疑您会需要某种机器学习来对它们进行分类。这是上一个讨论使用ML区分枪声和非枪声的线程：SVM for one Vs all acoustic signal classification