def compute_music_power(wav_filename,tf_config,
normalize_factor,
fftLen,stft_step,
min_freq,max_freq,src_num,
music_win_size,music_step):
setting={}
# read wav
print "... reading", wav_filename
wav_data=simmch.read_mch_wave(wav_filename)
wav=wav_data["wav"]/normalize_factor
fs=wav_data["framerate"]
# print info
print "# #channels : ", wav_data["nchannels"]
setting["nchannels"]=wav_data["nchannels"]
print "# sample size : ", wav.shape[1]
setting["nsamples"]=wav.shape[1]
print "# sampling rate : ", fs,"Hz"
setting["framerate"]=fs
print "# duration : ", wav_data["duration"],"sec"
setting["duration"]=wav_data["duration"]
# reading data
df=fs*1.0/fftLen
# cutoff bin
min_freq_bin=int(np.ceil(min_freq/df))
max_freq_bin=int(np.floor(max_freq/df))
print "# min freq. :",min_freq_bin*df , "Hz"
setting["min_freq"]=min_freq_bin*df
print "# max freq. :",max_freq_bin*df , "Hz"
setting["max_freq"]=max_freq_bin*df
print "# freq. step:",df, "Hz"
setting["freq_step"]=df
print "# min freq. bin index:",min_freq_bin
print "# max freq. bin index:",max_freq_bin
# apply STFT
win = hamming(fftLen) # ハミング窓
spec=simmch.stft_mch(wav,win,stft_step)
spec_m=spec[:,:,min_freq_bin:max_freq_bin]
# apply MUSIC method
## power[frame, freq, direction_id]
print "# src_num:",src_num
setting["src_num"]=src_num
setting["step_ms"]=1000.0/fs*stft_step
setting["music_step_ms"]=1000.0/fs*stft_step*music_step
power=compute_music_spec(spec_m,src_num,tf_config,df,min_freq_bin,
win_size=music_win_size,
step=music_step)
p=np.sum(np.real(power),axis=1)
m_power=10*np.log10(p+1.0)
m_full_power=10*np.log10(np.real(power)+1.0)
return spec,m_power,m_full_power,setting
type=str, metavar="FILE") (options, args) = parser.parse_args() # argv check if len(args)<2: print >>sys.stderr, "Usage: music.py <in: src.wav> <in: desired.wav>" quit() # read tf npr.seed(1234) # read wav (src) wav_filename1=args[0] print "... reading", wav_filename1 wav_data1=simmch.read_mch_wave(wav_filename1) wav1=wav_data1["wav"]/32767.0 fs1=wav_data1["framerate"] nch1=wav_data1["nchannels"] # print info print "# channel num : ", nch1 print "# sample size : ", wav1.shape print "# sampling rate : ", fs1 print "# sec : ", wav_data1["duration"] # read wav (desired) wav_data_list=[] for wav_filename2 in args[1:]: print "... reading", wav_filename2 wav_data2=simmch.read_mch_wave(wav_filename2) wav2=wav_data2["wav"]/32767.0
help="volumes of input sound (0<=v<=1)",
default=1.0,
type=str,
metavar="VOL")
(options, args) = parser.parse_args()
# argv check
if len(args) < 1:
quit()
#
npr.seed(1234)
src_volume = options.volume
output_filename = options.output_file
data = []
#
wav_filename = args[0]
print "... reading", wav_filename
wav_data = simmch.read_mch_wave(wav_filename)
wav = wav_data["wav"]
fs = wav_data["framerate"]
nch = wav_data["nchannels"]
amp = np.max(np.abs(wav))
print "[INFO] max amplitude:", amp
g = 32767.0 / amp * src_volume
print "[INFO] gain:", g
wav = wav * g
# save data
if output_filename != None:
simmch.save_mch_wave(wav, output_filename)
## read tf print "... reading", tf_filename tf_config=read_hark_tf(tf_filename) mic_pos=read_hark_tf_param(tf_filename) src_index=simmch.nearest_direction_index(tf_config,src_theta) print "# mic positions :",mic_pos print "# direction index:",src_index if not src_index in tf_config["tf"]: print >>sys.stderr, "Error: tf index",src_index,"does not exist in TF file" quit() ## read wav file print "... reading", wav_filename wav_data=simmch.read_mch_wave(wav_filename) scale=32767.0 wav=wav_data["wav"]/scale fs=wav_data["framerate"] nch=wav_data["nchannels"] ## print info print "# channel num : ", nch print "# sample size : ", wav.shape print "# sampling rate : ", fs print "# sec : ", wav_data["duration"] mono_wavdata = wav[0,:] ## apply TF fftLen = 512 step = fftLen / 4 mch_wavdata=apply_tf(mono_wavdata,fftLen, step,tf_config,src_index)
default=None,
type=str,
metavar="FILE")
(options, args) = parser.parse_args()
# argv check
if len(args) < 2:
print >> sys.stderr, "Usage: music.py <in: src.wav> <in: desired.wav>"
quit()
# read tf
npr.seed(1234)
# read wav (src)
wav_filename1 = args[0]
print "... reading", wav_filename1
wav_data1 = simmch.read_mch_wave(wav_filename1)
wav1 = wav_data1["wav"] / 32767.0
fs1 = wav_data1["framerate"]
nch1 = wav_data1["nchannels"]
# print info
print "# channel num : ", nch1
print "# sample size : ", wav1.shape
print "# sampling rate : ", fs1
print "# sec : ", wav_data1["duration"]
# read wav (desired)
wav_data_list = []
for wav_filename2 in args[1:]:
print "... reading", wav_filename2
wav_data2 = simmch.read_mch_wave(wav_filename2)
wav2 = wav_data2["wav"] / 32767.0
