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 numpy as np 31 32def hangover(lags, num_frames=10): 33 lags = lags.copy() 34 count = 0 35 last_lag = 0 36 37 for i in range(len(lags)): 38 lag = lags[i] 39 40 if lag == 0: 41 if count < num_frames: 42 lags[i] = last_lag 43 count += 1 44 else: 45 count = 0 46 last_lag = lag 47 48 return lags 49 50 51def smooth_pitch_lags(lags, d=2): 52 53 assert d < 4 54 55 num_silk_frames = len(lags) // 4 56 57 smoothed_lags = lags.copy() 58 59 tmp = np.arange(1, d+1) 60 kernel = np.concatenate((tmp, [d+1], tmp[::-1]), dtype=np.float32) 61 kernel = kernel / np.sum(kernel) 62 63 last = lags[0:d][::-1] 64 for i in range(num_silk_frames): 65 frame = lags[i * 4: (i+1) * 4] 66 67 if np.max(np.abs(frame)) == 0: 68 last = frame[4-d:] 69 continue 70 71 if i == num_silk_frames - 1: 72 next = frame[4-d:][::-1] 73 else: 74 next = lags[(i+1) * 4 : (i+1) * 4 + d] 75 76 if np.max(np.abs(next)) == 0: 77 next = frame[4-d:][::-1] 78 79 if np.max(np.abs(last)) == 0: 80 last = frame[0:d][::-1] 81 82 smoothed_frame = np.convolve(np.concatenate((last, frame, next), dtype=np.float32), kernel, mode='valid') 83 84 smoothed_lags[i * 4: (i+1) * 4] = np.round(smoothed_frame) 85 86 last = frame[4-d:] 87 88 return smoothed_lags 89 90def calculate_acorr_window(x, frame_size, lags, history=None, max_lag=300, radius=2, add_double_lag_acorr=False, no_pitch_threshold=32): 91 eps = 1e-9 92 93 lag_multiplier = 2 if add_double_lag_acorr else 1 94 95 if history is None: 96 history = np.zeros(lag_multiplier * max_lag + radius, dtype=x.dtype) 97 98 offset = len(history) 99 100 assert offset >= max_lag + radius 101 assert len(x) % frame_size == 0 102 103 num_frames = len(x) // frame_size 104 lags = lags.copy() 105 106 x_ext = np.concatenate((history, x), dtype=x.dtype) 107 108 d = radius 109 num_acorrs = 2 * d + 1 110 acorrs = np.zeros((num_frames, lag_multiplier * num_acorrs), dtype=x.dtype) 111 112 for idx in range(num_frames): 113 lag = lags[idx].item() 114 frame = x_ext[offset + idx * frame_size : offset + (idx + 1) * frame_size] 115 116 for k in range(lag_multiplier): 117 lag1 = (k + 1) * lag if lag >= no_pitch_threshold else lag 118 for j in range(num_acorrs): 119 past = x_ext[offset + idx * frame_size - lag1 + j - d : offset + (idx + 1) * frame_size - lag1 + j - d] 120 acorrs[idx, j + k * num_acorrs] = np.dot(frame, past) / np.sqrt(np.dot(frame, frame) * np.dot(past, past) + eps) 121 122 return acorrs, lags