|
1 /* Copyright (c) 2011 Xiph.Org Foundation |
|
2 Written by Jean-Marc Valin */ |
|
3 /* |
|
4 Redistribution and use in source and binary forms, with or without |
|
5 modification, are permitted provided that the following conditions |
|
6 are met: |
|
7 |
|
8 - Redistributions of source code must retain the above copyright |
|
9 notice, this list of conditions and the following disclaimer. |
|
10 |
|
11 - Redistributions in binary form must reproduce the above copyright |
|
12 notice, this list of conditions and the following disclaimer in the |
|
13 documentation and/or other materials provided with the distribution. |
|
14 |
|
15 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS |
|
16 ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT |
|
17 LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR |
|
18 A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE FOUNDATION OR |
|
19 CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, |
|
20 EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, |
|
21 PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR |
|
22 PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF |
|
23 LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING |
|
24 NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS |
|
25 SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
|
26 */ |
|
27 |
|
28 #ifndef ANALYSIS_H |
|
29 #define ANALYSIS_H |
|
30 |
|
31 #include "celt.h" |
|
32 #include "opus_private.h" |
|
33 |
|
34 #define NB_FRAMES 8 |
|
35 #define NB_TBANDS 18 |
|
36 #define NB_TOT_BANDS 21 |
|
37 #define ANALYSIS_BUF_SIZE 720 /* 15 ms at 48 kHz */ |
|
38 |
|
39 #define DETECT_SIZE 200 |
|
40 |
|
41 typedef struct { |
|
42 float angle[240]; |
|
43 float d_angle[240]; |
|
44 float d2_angle[240]; |
|
45 opus_val32 inmem[ANALYSIS_BUF_SIZE]; |
|
46 int mem_fill; /* number of usable samples in the buffer */ |
|
47 float prev_band_tonality[NB_TBANDS]; |
|
48 float prev_tonality; |
|
49 float E[NB_FRAMES][NB_TBANDS]; |
|
50 float lowE[NB_TBANDS]; |
|
51 float highE[NB_TBANDS]; |
|
52 float meanE[NB_TOT_BANDS]; |
|
53 float mem[32]; |
|
54 float cmean[8]; |
|
55 float std[9]; |
|
56 float music_prob; |
|
57 float Etracker; |
|
58 float lowECount; |
|
59 int E_count; |
|
60 int last_music; |
|
61 int last_transition; |
|
62 int count; |
|
63 float subframe_mem[3]; |
|
64 int analysis_offset; |
|
65 /** Probability of having speech for time i to DETECT_SIZE-1 (and music before). |
|
66 pspeech[0] is the probability that all frames in the window are speech. */ |
|
67 float pspeech[DETECT_SIZE]; |
|
68 /** Probability of having music for time i to DETECT_SIZE-1 (and speech before). |
|
69 pmusic[0] is the probability that all frames in the window are music. */ |
|
70 float pmusic[DETECT_SIZE]; |
|
71 float speech_confidence; |
|
72 float music_confidence; |
|
73 int speech_confidence_count; |
|
74 int music_confidence_count; |
|
75 int write_pos; |
|
76 int read_pos; |
|
77 int read_subframe; |
|
78 AnalysisInfo info[DETECT_SIZE]; |
|
79 } TonalityAnalysisState; |
|
80 |
|
81 void tonality_analysis(TonalityAnalysisState *tonal, AnalysisInfo *info, |
|
82 const CELTMode *celt_mode, const void *x, int len, int offset, int c1, int c2, int C, int lsb_depth, downmix_func downmix); |
|
83 |
|
84 void tonality_get_info(TonalityAnalysisState *tonal, AnalysisInfo *info_out, int len); |
|
85 |
|
86 void run_analysis(TonalityAnalysisState *analysis, const CELTMode *celt_mode, const void *analysis_pcm, |
|
87 int analysis_frame_size, int frame_size, int c1, int c2, int C, opus_int32 Fs, |
|
88 int lsb_depth, downmix_func downmix, AnalysisInfo *analysis_info); |
|
89 |
|
90 #endif |