百度AI的语音识别与语音合成

机器人语音问答的需要，调用百度AI的语音识别

这里的思路很简单，就是用百度的API，初始化客户端，然后输入参数进行调用。

代码

  
  
import wave
import pyaudio
from aip import AipSpeech,AipNlp
from playsound import playsound

""" 你的 APPID AK SK """
APP_ID = '****'
API_KEY = '****'
SECRET_KEY = '****'

# 读取文件
def get_file_content(filePath):
with open(filePath, 'rb') as fp:
return fp.read()


# 录音功能
def record_content():
CHUNK = 1024
FORMAT = pyaudio.paInt16
CHANNELS = 1
RATE = 16000
RECORD_SECONDS = 3

WAVE_OUTPUT_FILENAME = "audio.wav"
p = pyaudio.PyAudio()
stream = p.open(format=FORMAT, channels=CHANNELS,
rate=RATE, input= True,
frames_per_buffer=CHUNK)
print( "* recording")

frames = []
for j in range( 0, int(RATE / CHUNK * RECORD_SECONDS)):
data = stream.read(CHUNK)
frames.append(data)

print( "* done recording")

stream.stop_stream()
stream.close()
p.terminate()

wf = wave.open(WAVE_OUTPUT_FILENAME, 'wb')
wf.setnchannels(CHANNELS)
wf.setsampwidth(p.get_sample_size(FORMAT))
wf.setframerate(RATE)
wf.writeframes( b''.join(frames))
wf.close()
print( "done ------------------------------ ")
return WAVE_OUTPUT_FILENAME


# 生成语音功能客户端
client_audio = AipSpeech(APP_ID, API_KEY, SECRET_KEY)

# 语音录制
filePath = record_content()

# 语音识别
result_audio = client_audio.asr(get_file_content(filePath), 'wav', 16000, {
'dev_pid': 1536,
})
content_audio = result_audio[ 'result'][ 0]
print(content_audio)


# 自然语音处理客户端
client_nlp = AipNlp(APP_ID, API_KEY, SECRET_KEY)

# text = "百度是一家高科技公司"
text = content_audio

""" 调用词法分析 """
xx = client_nlp.lexer(text)
content_answer = xx[ 'items'][ 0][ 'item']

# 语音合成
try:
result_answer = client_audio.synthesis(content_answer, 'zh', 1, {
'vol': 5,
})
except Exception as e:
print(e)

# 语音写入
if not isinstance(result_answer, dict):
with open( 'audio.mp3', 'wb') as f:
f.write(result_answer)

# 语音播放
playsound( 'audio.mp3')
  
  

录音

首先将对方的语音录下，存为 **.wav 音频文件，其中原始 PCM 的录音参数必须符合 16k 采样率、16bit 位深、单声道，支持的格式有：pcm（不压缩）、wav（不压缩，pcm编码）、amr（压缩格式）

  
  
# 录音功能
def record_content():
CHUNK = 1024
FORMAT = pyaudio.paInt16
CHANNELS = 1
RATE = 16000
RECORD_SECONDS = 3

WAVE_OUTPUT_FILENAME = "audio.wav"
p = pyaudio.PyAudio()
stream = p.open(format=FORMAT, channels=CHANNELS,
rate=RATE, input= True,
frames_per_buffer=CHUNK)
print( "* recording")

frames = []
for j in range( 0, int(RATE / CHUNK * RECORD_SECONDS)):
data = stream.read(CHUNK)
frames.append(data)

print( "* done recording")

stream.stop_stream()
stream.close()
p.terminate()

wf = wave.open(WAVE_OUTPUT_FILENAME, 'wb')
wf.setnchannels(CHANNELS)
wf.setsampwidth(p.get_sample_size(FORMAT))
wf.setframerate(RATE)
wf.writeframes( b''.join(frames))
wf.close()
print( "done ------------------------------ ")
return WAVE_OUTPUT_FILENAME

  
  

 

识别

然后将录音文件进行识别

代码如下

  
  
# 语音识别
result_audio = client_audio.asr(get_file_content(filePath), 'wav', 16000, {
'dev_pid': 1536,
})
content_audio = result_audio[ 'result'][ 0]
print(content_audio)
  
  

处理

  
  
# 自然语音处理客户端
client_nlp = AipNlp(APP_ID, API_KEY, SECRET_KEY)

# text = "百度是一家高科技公司"
text = content_audio

""" 调用词法分析 """
xx = client_nlp.lexer(text)
content_answer = xx[ 'items'][ 0][ 'item']
  
  

 

回答

语音文件识别结束之后，将其写入到本地文件，并进行播放（python几种播放方法）

  
  
# 语音合成
try:
result_answer = client_audio.synthesis(content_answer, 'zh', 1, {
'vol': 5,
})
except Exception as e:
print(e)

# 语音写入
if not isinstance(result_answer, dict):
with open( 'audio.mp3', 'wb') as f:
f.write(result_answer)

# 语音播放
playsound( 'audio.mp3')
  
  

需要解决的问题（有建议请评论告知，感谢！）：

1.不定长语音文件的判定（音频文件时长不固定，根据说话时长来确定）

扫描二维码关注公众号，回复： 10335435 查看本文章

2.一群人中确定一个说话人接收指令