大家好，我是痞子衡，是正经搞技术的痞子。今天痞子衡给大家介绍的是语音处理工具pzh-py-speech诞生之音频录播实现。
音频录播是pzh-py-speech的主要功能，pzh-py-speech借助的是Python自带wave库以及第三方PyAudio库来实现的音频播放和录制功能，今天痞子衡为大家介绍音频录播在pzh-py-speech中是如何实现的。
一、wave简介
wave是python标准库，其可以实现wav音频文件的读写，并且能解析wav音频的参数。pzh-py-speech借助wave库来读写wav文件，播放音频时借助wave库来读取wav文件并获取音频参数（通道，采样宽度，采样率），录制音频时借助wave库来设置音频参数并保存成wav文件。下面列举了pzh-py-speech所用到的全部API：
wave.open()
# wav音频读API
Wave_read.getnchannels() # 获取音频通道数
Wave_read.getsampwidth() # 获取音频采样宽度
Wave_read.getframerate() # 获取音频采样率
Wave_read.getnframes() # 获取音频总帧数
Wave_read.readframes(n) # 读取音频帧数据
Wave_read.tell() # 获取已读取的音频帧数
Wave_read.close()
# wav音频写API
Wave_write.setnchannels(n) # 设置音频通道数
Wave_write.setsampwidth(n) # 设置音频采样宽度
Wave_write.setframerate(n) # 设置音频采样率
Wave_write.writeframes(data) # 写入音频帧数据
Wave_write.close()
二、PyAudio简介
PyAudio是开源跨平台音频库PortAudio的python封装，PyAudio库的维护者是Hubert Pham，该库从2006年开始推出，一直持续更新至今，pzh-py-speech使用的是PyAudio 0.2.11。
pzh-py-speech借助PyAudio库来实现音频数据流控制（包括从PC麦克风获取音频流，将音频流输出给PC扬声器），如果说wave库实现的是对wav文件的单纯操作，那么PyAudio库则实现的是音频相关硬件设备的交互。
PyAudio项目的官方主页如下：
- PortAudio官方主页: http://www.portaudio.com/
- PyAudio官方主页: http://people.csail.mit.edu/hubert/pyaudio/
- PyAudio安装方法: https://pypi.org/project/PyAudio/
PyAudio对音频流的控制有两种，一种是阻塞式的，另一种是非阻塞式的(callback)，前者一般用于确定的音频控制（比如单纯播放一个本地音频文件，并且中途不会有暂停/继续等操作），后者一般用于灵活的音频控制（比如录制一段音频，但是要等待一个事件响应才会结束）。pzh-py-speech用的是后者。下面是两种方式的音频播放使用示例：
import pyaudio
import wave
CHUNK = 1024
wf = wave.open(“test.wav”, 'rb')
p = pyaudio.PyAudio()
##########################################################
# 此为阻塞式，循环读取1024个byte音频数据去播放，直到test.wav文件数据被全部读出
stream = p.open(format=p.get_format_from_width(wf.getsampwidth()),
channels=wf.getnchannels(),
rate=wf.getframerate(),
output=True)
data = wf.readframes(CHUNK)
while data != '':
stream.write(data)
data = wf.readframes(CHUNK)
##########################################################
# 此为非阻塞式的(callback)，系统会自动读取test.wav文件里的音频帧，直到播放完毕
def callback(in_data, frame_count, time_info, status):
data = wf.readframes(frame_count)
return (data, pyaudio.paContinue)
stream = p.open(format=p.get_format_from_width(wf.getsampwidth()),
channels=wf.getnchannels(),
rate=wf.getframerate(),
output=True,
stream_callback=callback)
stream.start_stream()
while stream.is_active():
time.sleep(0.1)
##########################################################
stream.stop_stream()
stream.close()
p.terminate()
三、pzh-py-speech音频录播实现
3.1 播放实现
播放功能本身实现不算复杂，但pzh-py-speech里实现的是播放按钮的五种状态Start -> Play -> Pause -> Resume -> End控制，即播放中途实现了暂停和恢复，因此代码要稍微复杂一些。此处的重点是playAudioCallback()函数里的else分支，如果在暂停状态下，必须还是要给PyAudio返回一段空数据：
import wave
import pyaudio
AUDIO_PLAY_STATE_START = 0
AUDIO_PLAY_STATE_PLAY = 1
AUDIO_PLAY_STATE_PAUSE = 2
AUDIO_PLAY_STATE_RESUME = 3
AUDIO_PLAY_STATE_END = 4
class mainWin(win.speech_win):
def __init__(self, parent):
# ...
# Start -> Play -> Pause -> Resume -> End
self.playState = AUDIO_PLAY_STATE_START
def viewAudio( self, event ):
self.wavPath = self.m_genericDirCtrl_audioDir.GetFilePath()
if self.playState != AUDIO_PLAY_STATE_START:
self.playState = AUDIO_PLAY_STATE_END
self.m_button_play.SetLabel('Play Start')
def playAudioCallback(self, in_data, frame_count, time_info, status):
if self.playState == AUDIO_PLAY_STATE_PLAY or self.playState == AUDIO_PLAY_STATE_RESUME:
data = self.wavFile.readframes(frame_count)
if self.wavFile.getnframes() == self.wavFile.tell():
status = pyaudio.paComplete
self.playState = AUDIO_PLAY_STATE_END
self.m_button_play.SetLabel('Play Start')
else:
status = pyaudio.paContinue
return (data, status)
else:
# Note!!!:
data = numpy.zeros(frame_count*self.wavFile.getnchannels()).tostring()
return (data, pyaudio.paContinue)
def playAudio( self, event ):
if os.path.isfile(self.wavPath):
if self.playState == AUDIO_PLAY_STATE_END:
self.playState = AUDIO_PLAY_STATE_START
self.wavStream.stop_stream()
self.wavStream.close()
self.wavPyaudio.terminate()
self.wavFile.close()
if self.playState == AUDIO_PLAY_STATE_START:
self.playState = AUDIO_PLAY_STATE_PLAY
self.m_button_play.SetLabel('Play Pause')
self.wavFile = wave.open(self.wavPath, "rb")
self.wavPyaudio = pyaudio.PyAudio()
self.wavStream = self.wavPyaudio.open(format=self.wavPyaudio.get_format_from_width(self.wavFile.getsampwidth()),
channels=self.wavFile.getnchannels(),
rate=self.wavFile.getframerate(),
output=True,
stream_callback=self.playAudioCallback)
self.wavStream.start_stream()
elif self.playState == AUDIO_PLAY_STATE_PLAY or self.playState == AUDIO_PLAY_STATE_RESUME:
self.playState = AUDIO_PLAY_STATE_PAUSE
self.m_button_play.SetLabel('Play Resume')
elif self.playState == AUDIO_PLAY_STATE_PAUSE:
self.playState = AUDIO_PLAY_STATE_RESUME
self.m_button_play.SetLabel('Play Pause')
else:
pass
3.2 录制实现
相比播放功能，录制功能就简单了些，因为录制按钮状态就两种Start -> End，暂不支持中断后继续录制。这里的重点主要是音频三大参数（采样宽度，采样率，通道数）设置的支持：
import wave
import pyaudio
class mainWin(win.speech_win):
def recordAudioCallback(self, in_data, frame_count, time_info, status):
if not self.isRecording:
status = pyaudio.paComplete
else:
self.wavFrames.append(in_data)
status = pyaudio.paContinue
return (in_data, status)
def recordAudio( self, event ):
if not self.isRecording:
self.isRecording = True
self.m_button_record.SetLabel('Record Stop')
# Get the wave parameter from user settings
fileName = self.m_textCtrl_recFileName.GetLineText(0)
if fileName == '':
fileName = 'rec_untitled1.wav'
self.wavPath = os.path.join(os.path.dirname(os.path.abspath(os.path.dirname(__file__))), 'conv', 'rec', fileName)
self.wavSampRate = int(self.m_choice_sampRate.GetString(self.m_choice_sampRate.GetSelection()))
channels = self.m_choice_channels.GetString(self.m_choice_channels.GetSelection())
if channels == 'Mono':
self.wavChannels = 1
else: #if channels == 'Stereo':
self.wavChannels = 2
bitDepth = int(self.m_choice_bitDepth.GetString(self.m_choice_bitDepth.GetSelection()))
if bitDepth == 8:
self.wavBitFormat = pyaudio.paInt8
elif bitDepth == 24:
self.wavBitFormat = pyaudio.paInt24
elif bitDepth == 32:
self.wavBitFormat = pyaudio.paFloat32
else:
self.wavBitFormat = pyaudio.paInt16
# Record audio according to wave parameters
self.wavFrames = []
self.wavPyaudio = pyaudio.PyAudio()
self.wavStream = self.wavPyaudio.open(format=self.wavBitFormat,
channels=self.wavChannels,
rate=self.wavSampRate,
input=True,
frames_per_buffer=AUDIO_CHUNK_SIZE,
stream_callback=self.recordAudioCallback)
self.wavStream.start_stream()
else:
self.isRecording = False
self.m_button_record.SetLabel('Record Start')
self.wavStream.stop_stream()
self.wavStream.close()
self.wavPyaudio.terminate()
# Save the wave data into file
wavFile = wave.open(self.wavPath, 'wb')
wavFile.setnchannels(self.wavChannels)
wavFile.setsampwidth(self.wavPyaudio.get_sample_size(self.wavBitFormat))
wavFile.setframerate(self.wavSampRate)
wavFile.writeframes(b''.join(self.wavFrames))
wavFile.close()
至此，语音处理工具pzh-py-speech诞生之音频录播实现痞子衡便介绍完毕了，掌声在哪里~~~
参考文档
欢迎订阅
文章会同时发布到我的 博客园主页、CSDN主页、微信公众号 平台上。
微信搜索"痞子衡嵌入式"或者扫描下面二维码，就可以在手机上第一时间看了哦。
