Slengths) num_plots = len(spec_templates) num_rows = 2 num_cols = num_plots/num_rows+1 for i in xrange(len(spec_templates)): plt.subplot(num_cols,num_rows,i+1) plt.imshow(spec_templates[i].T[::-1],interpolation='nearest') plt.savefig('aar1_spec_templates_%d.png' % num_mix) np.savez('aar1_templates_%d.npz' % num_mix, templates) np.save('aar1_affinities_%d.npy' % num_mix, bem.affinities) test_path = '/home/mark/Template-Speech-Recognition/Data/Test/' test_file_indices = gtrd.get_data_files_indices(test_path) test_example_lengths = gtrd.get_detect_lengths(test_file_indices,test_path) np.save("data/test_example_lengths.npy",test_example_lengths) np.save("data/test_file_indices.npy",test_file_indices) import collections FOMS = collections.defaultdict(list) bgd = np.clip(np.load("data/aar_bgd_mel.npy"),.1,.4) test_example_lengths =np.load("data/test_example_lengths.npy") test_path = "/home/mark/Template-Speech-Recognition/Data/Test/" test_file_indices =np.load("data/test_file_indices.npy") for num_mix in num_mix_params: templates = tuple(np.clip(T,.01,.99) for T in (np.load('aar1_templates_%d.npz' % num_mix))['arr_0']) detection_array = np.zeros((test_example_lengths.shape[0], test_example_lengths.max() + 2),dtype=np.float32)
def get_params( args, sample_rate=16000, num_window_samples=320, num_window_step_samples=80, fft_length=512, kernel_length=7, freq_cutoff=3000, use_mel=False, ): # we get the basic file paths right here # TODO: make this system adaptive root_path = "/home/mark/Template-Speech-Recognition/" utterances_path = "/home/mark/Template-Speech-Recognition/Data/Train/" try: file_indices = np.load("data_parts/train_file_indices.npy") except: file_indices = gtrd.get_data_files_indices(utterances_path) np.save("data_parts/train_file_indices.npy", file_indices) num_mix_params = [1, 2, 3, 5, 7, 9] test_path = "/home/mark/Template-Speech-Recognition/Data/Test/" train_path = "/home/mark/Template-Speech-Recognition/Data/Train/" try: test_example_lengths = np.load("data_parts/test_example_lengths.npy") test_file_indices = np.load("data_parts/test_file_indices.npy") except: test_file_indices = gtrd.get_data_files_indices(test_path) test_example_lengths = gtrd.get_detect_lengths(test_file_indices, test_path) np.save("data_parts/test_example_lengths.npy", test_example_lengths) np.save("data_parts/test_file_indices.npy", test_file_indices) try: train_example_lengths = np.load("data_parts/train_example_lengths.npy") train_file_indices = np.load("data_parts/train_file_indices.npy") except: train_file_indices = gtrd.get_data_files_indices(train_path) train_example_lengths = gtrd.get_detect_lengths(train_file_indices, train_path) np.save("data_parts/train_example_lengths.npy", train_example_lengths) np.save("data_parts/train_file_indices.npy", train_file_indices) return ( gtrd.SpectrogramParameters( sample_rate=16000, num_window_samples=320, num_window_step_samples=80, fft_length=512, kernel_length=7, freq_cutoff=3000, use_mel=args.use_mel, ), gtrd.makeEdgemapParameters( block_length=args.edgeMapBlockLength, spread_length=args.edgeMapSpreadLength, threshold=args.edgeMapThreshold, ), root_path, utterances_path, file_indices, num_mix_params, test_path, train_path, train_example_lengths, train_file_indices, test_example_lengths, test_file_indices, )
file_indices, syllable, num_examples=-1, verbose=True) clipped_bgd = np.clip(avg_bgd.E,.1,.4) np.save(tmp_data_path+'clipped_bgd_102012.npy',clipped_bgd) padded_examples, lengths = et.extend_examples_to_max(clipped_bgd,syllable_examples, return_lengths=True) aar_template, aar_registered = et.register_templates_time_zero(syllable_examples,min_prob=.01) test_example_lengths = gtrd.get_detect_lengths(data_path+'Test/') np.save(tmp_data_path+'test_example_lengths_102012.npy',test_example_lengths) detection_array = np.zeros((test_example_lengths.shape[0], test_example_lengths.max() + 2),dtype=np.float32) linear_filter,c = et.construct_linear_filter(aar_template, clipped_bgd) # need to state the syllable we are working with syllable = np.array(['aa','r']) detection_array,example_start_end_times, detection_lengths = gtrd.get_detection_scores(data_path+'Test/', detection_array,
Slengths) num_plots = len(spec_templates) num_rows = 2 num_cols = num_plots/num_rows+1 for i in xrange(len(spec_templates)): plt.subplot(num_cols,num_rows,i+1) plt.imshow(spec_templates[i].T[::-1],interpolation='nearest') plt.savefig('aar1_spec_templates_%d.png' % num_mix) np.savez('aar1_templates_%d.npz' % num_mix, templates) np.save('aar1_affinities_%d.npy' % num_mix, bem.affinities) train_path = '/home/mark/Template-Speech-Recognition/Data/Train/' train_file_indices = gtrd.get_data_files_indices(train_path) train_example_lengths = gtrd.get_detect_lengths(train_file_indices,train_path) np.save("data/train_example_lengths.npy",train_example_lengths) np.save("data/train_file_indices.npy",train_file_indices) import collections FOMS = collections.defaultdict(list) for num_mix in num_mix_params: templates = (np.load('aar1_templates_%d.npz' % num_mix))['arr_0'] detection_array = np.zeros((train_example_lengths.shape[0], train_example_lengths.max() + 2),dtype=np.float32) linear_filters_cs = et.construct_linear_filters(templates, bgd) np.savez('data/linear_filter_aar_%d.npy'% num_mix,linear_filters_cs[:][0]) np.savez('data/c_aar_%d.npy'%num_mix,np.array(linear_filters_cs[:][1])) syllable = np.array(['aa','r']) detection_array,example_start_end_times, detection_lengths = gtrd.get_detection_scores_mixture(train_path,