Mit der System.Speech.Synthesis.SpeechSynthesizer-Klasse in .NET 3.5 scheint die AudioPosition-Eigenschaft des SpeakProgressEventArgs ungenau zu sein.Sind die SpeakProgressEventArgs des SpeechSynthesizer ungenau?
Der folgende Code erzeugt die folgende Ausgabe:
Code:
using System;
using System.Speech.Synthesis;
using System.Threading;
namespace SpeechTest
{
class Program
{
static ManualResetEvent speechDoneEvent = new ManualResetEvent(false);
static void Main(string[] args)
{
SpeechSynthesizer synthesizer = new SpeechSynthesizer();
synthesizer.SpeakProgress += new EventHandler<SpeakProgressEventArgs>(synthesizer_SpeakProgress);
synthesizer.SpeakCompleted += new EventHandler<SpeakCompletedEventArgs>(synthesizer_SpeakCompleted);
synthesizer.SetOutputToWaveFile("Test.wav");
synthesizer.SpeakAsync("This holiday season, support the music you love by shopping at Made in Washington, online and at one of five local stores. Made in Washington chocolates, bountiful gift baskets and ornaments are the perfect holiday gifts for family, friends and co-workers.");
speechDoneEvent.WaitOne();
}
static void synthesizer_SpeakCompleted(object sender, SpeakCompletedEventArgs e)
{
speechDoneEvent.Set();
}
static void synthesizer_SpeakProgress(object sender, SpeakProgressEventArgs e)
{
Console.WriteLine("SpeakProgress: AudioPosition=" + e.AudioPosition + ",\tCharacterPosition=" + e.CharacterPosition + ",\tCharacterCount=" + e.CharacterCount + ",\tText=" + e.Text);
}
}
}
Ausgang:
SpeakProgress: AudioPosition=00:00:00.0043750, CharacterPosition=0, CharacterCount=4, Text=This
SpeakProgress: AudioPosition=00:00:00.2925625, CharacterPosition=5, CharacterCount=7, Text=holiday
SpeakProgress: AudioPosition=00:00:00.9086250, CharacterPosition=13, CharacterCount=6, Text=season
SpeakProgress: AudioPosition=00:00:01.9421250, CharacterPosition=21, CharacterCount=7, Text=support
SpeakProgress: AudioPosition=00:00:02.5621250, CharacterPosition=29, CharacterCount=3, Text=the
SpeakProgress: AudioPosition=00:00:02.6760625, CharacterPosition=33, CharacterCount=5, Text=music
SpeakProgress: AudioPosition=00:00:03.2648125, CharacterPosition=39, CharacterCount=3, Text=you
SpeakProgress: AudioPosition=00:00:03.5199375, CharacterPosition=43, CharacterCount=4, Text=love
SpeakProgress: AudioPosition=00:00:03.8435625, CharacterPosition=48, CharacterCount=2, Text=by
SpeakProgress: AudioPosition=00:00:04.0701875, CharacterPosition=51, CharacterCount=8, Text=shopping
SpeakProgress: AudioPosition=00:00:04.6840625, CharacterPosition=60, CharacterCount=2, Text=at
SpeakProgress: AudioPosition=00:00:04.8036250, CharacterPosition=63, CharacterCount=4, Text=Made
SpeakProgress: AudioPosition=00:00:05.0698125, CharacterPosition=68, CharacterCount=2, Text=in
SpeakProgress: AudioPosition=00:00:05.2521250, CharacterPosition=71, CharacterCount=10, Text=Washington
SpeakProgress: AudioPosition=00:00:06.2961875, CharacterPosition=83, CharacterCount=6, Text=online
SpeakProgress: AudioPosition=00:00:07.0540625, CharacterPosition=90, CharacterCount=3, Text=and
SpeakProgress: AudioPosition=00:00:07.3331250, CharacterPosition=94, CharacterCount=2, Text=at
SpeakProgress: AudioPosition=00:00:07.6818750, CharacterPosition=97, CharacterCount=3, Text=one
SpeakProgress: AudioPosition=00:00:08.0598750, CharacterPosition=101, CharacterCount=2, Text=of
SpeakProgress: AudioPosition=00:00:08.2163750, CharacterPosition=104, CharacterCount=4, Text=five
SpeakProgress: AudioPosition=00:00:08.5971875, CharacterPosition=109, CharacterCount=5, Text=local
SpeakProgress: AudioPosition=00:00:09.0243750, CharacterPosition=115, CharacterCount=6, Text=stores
SpeakProgress: AudioPosition=00:00:10.5325625, CharacterPosition=123, CharacterCount=4, Text=Made
SpeakProgress: AudioPosition=00:00:10.7700625, CharacterPosition=128, CharacterCount=2, Text=in
SpeakProgress: AudioPosition=00:00:10.9377500, CharacterPosition=131, CharacterCount=10, Text=Washington
SpeakProgress: AudioPosition=00:00:11.6708125, CharacterPosition=142, CharacterCount=10, Text=chocolates
SpeakProgress: AudioPosition=00:00:12.9798750, CharacterPosition=154, CharacterCount=9, Text=bountiful
SpeakProgress: AudioPosition=00:00:13.6303125, CharacterPosition=164, CharacterCount=4, Text=gift
SpeakProgress: AudioPosition=00:00:14.0959375, CharacterPosition=169, CharacterCount=7, Text=baskets
SpeakProgress: AudioPosition=00:00:14.7848125, CharacterPosition=177, CharacterCount=3, Text=and
SpeakProgress: AudioPosition=00:00:15.0507500, CharacterPosition=181, CharacterCount=9, Text=ornaments
SpeakProgress: AudioPosition=00:00:15.7195000, CharacterPosition=191, CharacterCount=3, Text=are
SpeakProgress: AudioPosition=00:00:15.9872500, CharacterPosition=195, CharacterCount=3, Text=the
SpeakProgress: AudioPosition=00:00:16.1488750, CharacterPosition=199, CharacterCount=7, Text=perfect
SpeakProgress: AudioPosition=00:00:16.7275000, CharacterPosition=207, CharacterCount=7, Text=holiday
SpeakProgress: AudioPosition=00:00:17.3336875, CharacterPosition=215, CharacterCount=5, Text=gifts
SpeakProgress: AudioPosition=00:00:17.9813125, CharacterPosition=221, CharacterCount=3, Text=for
SpeakProgress: AudioPosition=00:00:18.2216875, CharacterPosition=225, CharacterCount=6, Text=family
SpeakProgress: AudioPosition=00:00:19.0973750, CharacterPosition=233, CharacterCount=7, Text=friends
SpeakProgress: AudioPosition=00:00:19.7726250, CharacterPosition=241, CharacterCount=3, Text=and
SpeakProgress: AudioPosition=00:00:19.9655625, CharacterPosition=245, CharacterCount=10, Text=co-workers
SpeakProgress: AudioPosition=00:00:20.2518750, CharacterPosition=245, CharacterCount=10, Text=co-workers
jedoch die Dauer der .wav-Datei erzeugt wird, ist 15,69 Sekunden. Das gleiche Verhalten tritt auf, wenn Sie einen Stream oder NULL ausgeben.
Die documentation für die Eigenschaft sagt, die Eigenschaft ist "Ein TimeSpan-Objekt, das die Zeitposition des Ereignisses im Audio-Ausgangsstrom darstellt".
Sollte es eine genaue Zeit sein, die die Zeit angibt, zu der das Wort in der Ausgabedatei gestartet oder beendet wurde, oder interpretiere ich es falsch?
Was ist die ausgewählte Stimme? – Ahmad