ict.xunfei/Assets/Scripts/kdl/Mp3TansformHuman.cs

using System.Collections;
using System.Collections.Generic;
using UnityEngine;
using System;
using System.IO;
using NAudio.Wave;

public class Mp3TansformHuman
{

    // parse mp3
    public static AudioClip LoadMp3Audio(byte[] audioBytes, string fileName)
    {
        MemoryStream mp3stream = new MemoryStream(audioBytes);
        Mp3FileReader mp3audio = new Mp3FileReader(mp3stream);
        WaveStream waveStream = WaveFormatConversionStream.CreatePcmStream(mp3audio);
        MemoryStream outputStream = new MemoryStream();
        using (WaveFileWriter waveFileWriter = new WaveFileWriter(outputStream, waveStream.WaveFormat))
        {
            byte[] bytes = new byte[waveStream.Length];
            waveStream.Position = 0;
            waveStream.Read(bytes, 0, Convert.ToInt32(waveStream.Length));
            waveFileWriter.Write(bytes, 0, bytes.Length);
            waveFileWriter.Flush();
        }
        byte[] wavBytes = outputStream.ToArray();
        return LoadWavAudio(wavBytes, fileName);
    }
    // parse wav
    public static AudioClip LoadWavAudio(byte[] audioBytes, string fileName)
    {
        // WAV 自定义wav解析类
        WAV wav = new WAV(audioBytes);
        AudioClip audioClip;
        if (wav.ChannelCount == 2)
        {
            audioClip = AudioClip.Create(fileName, wav.SampleCount, 2, wav.Frequency, false);
            audioClip.SetData(wav.StereoChannel, 0);
        }
        else
        {
            audioClip = AudioClip.Create(fileName, wav.SampleCount, 1, wav.Frequency, false);
            audioClip.SetData(wav.LeftChannel, 0);
        }
        return audioClip;
    }
    // 逻辑不完整，但是能用，所以只要你和代码一个能跑就可以了
    public class WAV
    {

        // convert two bytes to one float in the range -1 to 1
        static float bytesToFloat(byte firstByte, byte secondByte)
        {
            // convert two bytes to one short (little endian)
            short s = (short)((secondByte << 8) | firstByte);
            // convert to range from -1 to (just below) 1
            return s / 32768.0F;
        }

        static int bytesToInt(byte[] bytes, int offset = 0)
        {
            int value = 0;
            for (int i = 0; i < 4; i++)
            {
                value |= ((int)bytes[offset + i]) << (i * 8);
            }
            return value;
        }
        // properties
        public float[] LeftChannel { get; internal set; }
        public float[] RightChannel { get; internal set; }
        public float[] StereoChannel { get; internal set; }
        public int ChannelCount { get; internal set; }
        public int SampleCount { get; internal set; }
        public int Frequency { get; internal set; }


        public WAV(byte[] wav)
        {
            // Determine if mono or stereo
            ChannelCount = wav[22];     // Forget byte 23 as 99.999% of WAVs are 1 or 2 channels

            // Get the frequency
            Frequency = bytesToInt(wav, 24);

            // Get past all the other sub chunks to get to the data subchunk:
            int pos = 12;   // First Subchunk ID from 12 to 16

            // Keep iterating until we find the data chunk (i.e. 64 61 74 61 ...... (i.e. 100 97 116 97 in decimal))
            while (!(wav[pos] == 100 && wav[pos + 1] == 97 && wav[pos + 2] == 116 && wav[pos + 3] == 97))
            {
                pos += 4;
                int chunkSize = wav[pos] + wav[pos + 1] * 256 + wav[pos + 2] * 65536 + wav[pos + 3] * 16777216;
                pos += 4 + chunkSize;
            }
            pos += 8;

            // Pos is now positioned to start of actual sound data.
            SampleCount = (wav.Length - pos) / 2;     // 2 bytes per sample (16 bit sound mono)
            if (ChannelCount == 2) SampleCount /= 2;        // 4 bytes per sample (16 bit stereo)

            // Allocate memory (right will be null if only mono sound)
            LeftChannel = new float[SampleCount];
            if (ChannelCount == 2) RightChannel = new float[SampleCount];
            else RightChannel = null;

            // Write to double array/s:
            int i = 0;
            while (pos < wav.Length)
            {
                LeftChannel[i] = bytesToFloat(wav[pos], wav[pos + 1]);
                pos += 2;
                if (ChannelCount == 2)
                {
                    RightChannel[i] = bytesToFloat(wav[pos], wav[pos + 1]);
                    pos += 2;
                }
                i++;
            }

            //Merge left and right channels for stereo sound
            if (ChannelCount == 2)
            {
                StereoChannel = new float[SampleCount * 2];
                //Current position in our left and right channels
                int channelPos = 0;
                //After we've changed two values for our Stereochannel, we want to increase our channelPos
                short posChange = 0;

                for (int index = 0; index < (SampleCount * 2); index++)
                {

                    if (index % 2 == 0)
                    {
                        StereoChannel[index] = LeftChannel[channelPos];
                        posChange++;
                    }
                    else
                    {
                        StereoChannel[index] = RightChannel[channelPos];
                        posChange++;
                    }
                    //Two values have been changed, so update our channelPos
                    if (posChange % 2 == 0)
                    {
                        if (channelPos < SampleCount)
                        {
                            channelPos++;
                            //Reset the counter for next iterations
                            posChange = 0;
                        }
                    }
                }
            }
            else
            {
                StereoChannel = null;
            }

            Debug.Log($"mpegFile.Length={wav.Length},ChannelCount={ChannelCount},lenSample={LeftChannel.Length}");
        }
    }
}