1""" 2/* Copyright (c) 2023 Amazon 3 Written by Jan Buethe */ 4/* 5 Redistribution and use in source and binary forms, with or without 6 modification, are permitted provided that the following conditions 7 are met: 8 9 - Redistributions of source code must retain the above copyright 10 notice, this list of conditions and the following disclaimer. 11 12 - Redistributions in binary form must reproduce the above copyright 13 notice, this list of conditions and the following disclaimer in the 14 documentation and/or other materials provided with the distribution. 15 16 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 17 ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT 18 LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR 19 A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER 20 OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, 21 EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, 22 PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR 23 PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF 24 LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING 25 NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS 26 SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 27*/ 28""" 29 30import os 31 32import torch 33import numpy as np 34 35def load_features(feature_file, version=2): 36 if version == 2: 37 layout = { 38 'cepstrum': [0,18], 39 'periods': [18, 19], 40 'pitch_corr': [19, 20], 41 'lpc': [20, 36] 42 } 43 frame_length = 36 44 45 elif version == 1: 46 layout = { 47 'cepstrum': [0,18], 48 'periods': [36, 37], 49 'pitch_corr': [37, 38], 50 'lpc': [39, 55], 51 } 52 frame_length = 55 53 else: 54 raise ValueError(f'unknown feature version: {version}') 55 56 57 raw_features = torch.from_numpy(np.fromfile(feature_file, dtype='float32')) 58 raw_features = raw_features.reshape((-1, frame_length)) 59 60 features = torch.cat( 61 [ 62 raw_features[:, layout['cepstrum'][0] : layout['cepstrum'][1]], 63 raw_features[:, layout['pitch_corr'][0] : layout['pitch_corr'][1]] 64 ], 65 dim=1 66 ) 67 68 lpcs = raw_features[:, layout['lpc'][0] : layout['lpc'][1]] 69 periods = (0.1 + 50 * raw_features[:, layout['periods'][0] : layout['periods'][1]] + 100).long() 70 71 return {'features' : features, 'periods' : periods, 'lpcs' : lpcs} 72 73 74 75def create_new_data(signal_path, reference_data_path, new_data_path, offset=320, preemph_factor=0.85): 76 ref_data = np.memmap(reference_data_path, dtype=np.int16) 77 signal = np.memmap(signal_path, dtype=np.int16) 78 79 signal_preemph_path = os.path.splitext(signal_path)[0] + '_preemph.raw' 80 signal_preemph = np.memmap(signal_preemph_path, dtype=np.int16, mode='write', shape=signal.shape) 81 82 83 assert len(signal) % 160 == 0 84 num_frames = len(signal) // 160 85 mem = np.zeros(1) 86 for fr in range(len(signal)//160): 87 signal_preemph[fr * 160 : (fr + 1) * 160] = np.convolve(np.concatenate((mem, signal[fr * 160 : (fr + 1) * 160])), [1, -preemph_factor], mode='valid') 88 mem = signal[(fr + 1) * 160 - 1 : (fr + 1) * 160] 89 90 new_data = np.memmap(new_data_path, dtype=np.int16, mode='write', shape=ref_data.shape) 91 92 new_data[:] = 0 93 N = len(signal) - offset 94 new_data[1 : 2*N + 1: 2] = signal_preemph[offset:] 95 new_data[2 : 2*N + 2: 2] = signal_preemph[offset:] 96 97 98def parse_warpq_scores(output_file): 99 """ extracts warpq scores from output file """ 100 101 with open(output_file, "r") as f: 102 lines = f.readlines() 103 104 scores = [float(line.split("WARP-Q score:")[-1]) for line in lines if line.startswith("WARP-Q score:")] 105 106 return scores 107 108 109def parse_stats_file(file): 110 111 with open(file, "r") as f: 112 lines = f.readlines() 113 114 mean = float(lines[0].split(":")[-1]) 115 bt_mean = float(lines[1].split(":")[-1]) 116 top_mean = float(lines[2].split(":")[-1]) 117 118 return mean, bt_mean, top_mean 119 120def collect_test_stats(test_folder): 121 """ collects statistics for all discovered metrics from test folder """ 122 123 metrics = {'pesq', 'warpq', 'pitch_error', 'voicing_error'} 124 125 results = dict() 126 127 content = os.listdir(test_folder) 128 129 stats_files = [file for file in content if file.startswith('stats_')] 130 131 for file in stats_files: 132 metric = file[len("stats_") : -len(".txt")] 133 134 if metric not in metrics: 135 print(f"warning: unknown metric {metric}") 136 137 mean, bt_mean, top_mean = parse_stats_file(os.path.join(test_folder, file)) 138 139 results[metric] = [mean, bt_mean, top_mean] 140 141 return results 142