转换成16KHz采样率(含文件头)
void reSamplingAndSave(byte[] data) throws IOException, UnsupportedAudioFileException {
WaveFileReader reader = new WaveFileReader();
AudioInputStream audioIn = reader.getAudioInputStream(new ByteArrayInputStream(data)); AudioFormat srcFormat = audioIn.getFormat();
int targetSampleRate = 16000; AudioFormat dstFormat = new AudioFormat(srcFormat.getEncoding(),
targetSampleRate,
srcFormat.getSampleSizeInBits(),
srcFormat.getChannels(),
srcFormat.getFrameSize(),
srcFormat.getFrameRate(),
srcFormat.isBigEndian()); AudioInputStream convertedIn = AudioSystem.getAudioInputStream(dstFormat, audioIn); String fileName = System.getenv("TEMP").concat(File.separator).concat(System.currentTimeMillis()+".wav");
File file= new File(fileName);
WaveFileWriter writer = new WaveFileWriter();
writer.write(convertedIn, AudioFileFormat.Type.WAVE, file);
}
使用方法:
byte[] bytes = Files.readAllBytes(Paths.get("e:\\asset\\nZLWKJjQ.wav"));
重采样,不保留文件头(通常用于语音识别):
byte[] reSampling(byte[] data) throws IOException, UnsupportedAudioFileException { AudioInputStream audioIn = AudioSystem.getAudioInputStream(new ByteArrayInputStream(data)); AudioFormat srcFormat = audioIn.getFormat();
int targetSampleRate = 16000; AudioFormat dstFormat = new AudioFormat(srcFormat.getEncoding(),
targetSampleRate,
srcFormat.getSampleSizeInBits(),
srcFormat.getChannels(),
srcFormat.getFrameSize(),
srcFormat.getFrameRate(),
srcFormat.isBigEndian()); AudioInputStream convertedIn = AudioSystem.getAudioInputStream(dstFormat, audioIn); int numReads = -1; int BUFF_SIZE = targetSampleRate/2; byte [] buff = new byte[BUFF_SIZE]; ByteArrayOutputStream outputStream = new ByteArrayOutputStream();
while ((numReads = convertedIn.read(buff)) !=-1)
{
System.out.println("读入字节数:"+ numReads);
outputStream.write(buff);
}
return outputStream.toByteArray();
}
重采样2(不含文件头):
public static final int SAMPLE_RATE = 16000; // 16-bit audio
private static final int BYTES_PER_SAMPLE = 2;
// 16-bit audio
private static final int BITS_PER_SAMPLE = 16;
private static final double MAX_16_BIT = 32768;
private static final int SAMPLE_BUFFER_SIZE = 4096; private static final int MONO = 1;
private static final int STEREO = 2;
private static final boolean LITTLE_ENDIAN = false;
private static final boolean BIG_ENDIAN = true;
private static final boolean SIGNED = true;
private static final boolean UNSIGNED = false;
private static AudioFormat dstFormat = new AudioFormat(AudioFormat.Encoding.PCM_SIGNED,
SAMPLE_RATE,
BITS_PER_SAMPLE,
MONO,
BYTES_PER_SAMPLE,
8000,
LITTLE_ENDIAN);
public static byte[] reSamplingPCM(byte[] data) { try(AudioInputStream audioIn = AudioSystem.getAudioInputStream(new ByteArrayInputStream(data));
AudioInputStream convertedStream = AudioSystem.getAudioInputStream(dstFormat, audioIn);
ByteArrayOutputStream outputStream = new ByteArrayOutputStream()) { if (audioIn.getFormat().matches(dstFormat)) {
return data;
} int numReads = -1; int BUFF_SIZE = SAMPLE_RATE / 2; byte[] buff = new byte[BUFF_SIZE]; while ((numReads = convertedStream.read(buff)) != -1) {
log.info("read {} byte(s)", numReads);
outputStream.write(buff);
}
return outputStream.toByteArray();
} catch (UnsupportedAudioFileException |IOException e) {
log.error("occurs errors when re-sampling the audio stream:{}",e);
throw new RuntimeException("occurs errors when re-sampling the audio stream:{}",e);
}
}
参考来源:
https://stackoverflow.com/questions/15410725/java-resample-wav-soundfile-without-third-party-library
https://www.codota.com/web/assistant/code/rs/5c7689a149efcb00014e68b2#L54