train_data_path = root_path+'Data/Train/' file_indices = gtrd.get_data_files_indices(train_data_path) syllable = np.array(['aa','r']) avg_bgd, syllable_examples, backgrounds = gtrd.get_syllable_examples_backgrounds_files(train_data_path, 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'])
avg_bgd, syllable_examples, backgrounds = gtrd.get_syllables_examples_backgrounds_files(train_data_path, file_indices, syllables, log_part_blocks, log_invpart_blocks, num_examples=-1, verbose=True) clipped_bgd = np.clip(avg_bgd.E,.1,.4) np.save(tmp_data_path+'clipped_bgd_101812.npy',clipped_bgd) import template_speech_rec.estimate_template as et for syllable,examples in syllable_examples.items(): np.save(tmp_data_path+'%s_%s_examples.npy' % syllable, et.extend_examples_to_max(clipped_bgd,examples)) padded_examples_syllable_dict = dict( (syll, et.extend_examples_to_max(clipped_bgd,examples)) for syll, examples in syllable_examples.items()) del backgrounds # estimate mixture models # import template_speech_rec.bernoulli_mixture as bm mixture_models_syllable = {} for syllable, examples in padded_examples_syllable_dict.items():