Go to the documentation of this file.
39 512, 12,
ff_metasound_lsp8, 1, 5, 3, 3,
tab.
shape08, 8, 28, 20, 6, 40
48 512, 16,
ff_metasound_lsp11, 1, 6, 4, 3,
tab.
shape11, 9, 36, 30, 7, 90
57 512, 16,
ff_metasound_lsp11, 1, 6, 4, 3,
tab.
shape11, 9, 36, 30, 7, 90
66 1024, 16,
ff_metasound_lsp16, 1, 6, 4, 3,
tab.
shape16, 9, 56, 60, 7, 180
75 1024, 16,
ff_metasound_lsp22, 1, 6, 4, 3,
tab.
shape22_1, 9, 56, 36, 7, 144
84 1024, 16,
ff_metasound_lsp22, 1, 6, 4, 3,
tab.
shape22_1, 9, 56, 36, 7, 144
93 512, 16,
tab.
lsp22_2, 1, 6, 4, 4,
tab.
shape22_2, 9, 56, 36, 7, 72
102 2048, 20,
ff_metasound_lsp44, 1, 6, 4, 4,
tab.
shape44, 9, 84, 54, 7, 432
111 2048, 20,
ff_metasound_lsp44, 1, 6, 4, 4,
tab.
shape44, 9, 84, 54, 7, 432
140 if (x % 400 ||
b % 5)
146 rtab =
tabs[
b / 5].tab;
156 float ppc_gain,
float *speech,
int len)
160 const float *shape_end = shape +
len;
165 speech[
i] += ppc_gain * *shape++;
169 for (j = -
width / 2; j < (
width + 1) / 2; j++)
170 speech[j + center] += ppc_gain * *shape++;
175 for (j = -
width / 2; j < (
width + 1) / 2 && shape < shape_end; j++)
176 speech[j + center] += ppc_gain * *shape++;
180 const float *shape,
float *speech)
187 int period_range = max_period - min_period;
188 float pgain_step = 25000.0 / ((1 << mtab->
pgain_bit) - 1);
189 float ppc_gain = 1.0 / 8192 *
201 if (isampf == 22 && ibps == 32) {
212 int ch,
float *
out,
float gain,
217 float *hist = tctx->
bark_hist[ftype][ch];
218 float val = ((
const float []) { 0.4, 0.35, 0.28 })[ftype];
223 for (
i = 0;
i < fw_cb_len;
i++)
224 for (j = 0; j < bark_n_coef; j++, idx++) {
227 float st = use_hist ? (1.0 -
val) * tmp2 +
val * hist[idx] + 1.0
244 for (
i = 0;
i < tctx->
n_div[ftype];
i++) {
253 const uint8_t *buf,
int buf_size)
268 if (
bits->window_type > 8) {
280 for (j = 0; j <
sub; j++)
282 bits->bark1[
i][j][k] =
286 for (j = 0; j <
sub; j++)
295 for (j = 0; j <
sub; j++)
333 if (isampf < 8 || isampf > 44) {
361 if (ibps < 8 || ibps > 48) {
366 switch ((isampf << 8) + ibps) {
396 "This version does not support %d kHz - %d kbit/s/ch mode.\n",
410 "VQF TwinVQ should have only one frame per packet\n");
static int twinvq_read_bitstream(AVCodecContext *avctx, TwinVQContext *tctx, const uint8_t *buf, int buf_size)
@ AV_SAMPLE_FMT_FLTP
float, planar
static av_cold int init(AVCodecContext *avctx)
const TwinVQModeTab * mtab
uint64_t channel_layout
Audio channel layout.
uint8_t sub
Number subblocks in each frame.
static const uint16_t bark_tab_m22_256[]
int sample_rate
samples per second
uint8_t bits_main_spec[2][4][2]
bits for the main codebook
static float sub(float src0, float src1)
static enum AVSampleFormat sample_fmts[]
static const struct @94 tabs[]
static const uint16_t bark_tab_s44_128[]
static av_cold int twinvq_decode_init(AVCodecContext *avctx)
#define AV_CH_LAYOUT_MONO
static int get_bits_count(const GetBitContext *s)
TwinVQFrameData bits[TWINVQ_MAX_FRAMES_PER_PACKET]
uint8_t ppc_shape_len
size of PPC shape CB
av_cold int ff_twinvq_decode_init(AVCodecContext *avctx)
static const uint16_t bark_tab_s16_128[]
uint8_t pgain_bit
bits for PPC gain
static void skip_bits(GetBitContext *s, int n)
static unsigned int get_bits(GetBitContext *s, int n)
Read 1-25 bits.
static void add_peak(int period, int width, const float *shape, float ppc_gain, float *speech, int len)
Sum to data a periodic peak of a given period, width and shape.
#define TWINVQ_WINDOW_TYPE_BITS
uint8_t bark_n_coef
number of BSE CB coefficients to read
static const TwinVQModeTab mode_16_16
static const TwinVQModeTab mode_11_08
static const struct twinvq_data tab
static const TwinVQModeTab mode_08_08
static const TwinVQModeTab mode_22_24
static double val(void *priv, double ch)
static const uint16_t bark_tab_l08_512[]
static int very_broken_op(int a, int b)
Evaluate a * b / 400 rounded to the nearest integer.
uint16_t size
frame size in samples
static float twinvq_mulawinv(float y, float clip, float mu)
#define AV_CH_LAYOUT_STEREO
void(* dec_bark_env)(struct TwinVQContext *tctx, const uint8_t *in, int use_hist, int ch, float *out, float gain, enum TwinVQFrameType ftype)
int ff_twinvq_decode_frame(AVCodecContext *avctx, void *data, int *got_frame_ptr, AVPacket *avpkt)
void(* decode_ppc)(struct TwinVQContext *tctx, int period_coef, int g_coef, const float *shape, float *speech)
static const uint16_t bark_tab_m16_512[]
#define AV_LOG_ERROR
Something went wrong and cannot losslessly be recovered.
static int init_get_bits8(GetBitContext *s, const uint8_t *buffer, int byte_size)
Initialize GetBitContext.
static void decode(AVCodecContext *dec_ctx, AVPacket *pkt, AVFrame *frame, FILE *outfile)
static const uint16_t bark_tab_l16_1024[]
Parameters and tables that are different for every combination of bitrate/sample rate.
const uint16_t * bark_tab
static void twinvq_memset_float(float *buf, float val, int size)
const int16_t * bark_cb
codebook for the bark scale envelope (BSE)
av_cold int ff_twinvq_decode_close(AVCodecContext *avctx)
it s the only field you need to keep assuming you have a context There is some magic you don t need to care about around this just let it vf default minimum maximum flags name is the option keep it simple and lowercase description are in without period
int64_t bit_rate
the average bitrate
#define ROUNDED_DIV(a, b)
static unsigned int get_bits1(GetBitContext *s)
static const TwinVQModeTab mode_44_48
#define AV_CODEC_CAP_CHANNEL_CONF
Codec should fill in channel configuration and samplerate instead of container.
static const TwinVQModeTab mode_11_10
@ TWINVQ_FT_LONG
Long frame (single sub-block + PPC)
#define AV_CODEC_CAP_DR1
Codec uses get_buffer() or get_encode_buffer() for allocating buffers and supports custom allocators.
#define NULL_IF_CONFIG_SMALL(x)
Return NULL if CONFIG_SMALL is true, otherwise the argument without modification.
uint8_t bark_n_bit
number of bits of the BSE coefs
uint8_t ppc_period_bit
number of the bits for the PPC period value
uint64_t_TMPL AV_WL64 unsigned int_TMPL AV_WL32 unsigned int_TMPL AV_WL24 unsigned int_TMPL AV_WL16 uint64_t_TMPL AV_WB64 unsigned int_TMPL AV_RB32
static void decode_ppc(TwinVQContext *tctx, int period_coef, int g_coef, const float *shape, float *speech)
static const uint16_t bark_tab_s11_64[]
int bits_main_spec_change[4]
#define TWINVQ_CHANNELS_MAX
The reader does not expect b to be semantically here and if the code is changed by maybe adding a a division or other the signedness will almost certainly be mistaken To avoid this confusion a new type was SUINT is the C unsigned type but it holds a signed int to use the same example SUINT a
uint16_t peak_per2wid
constant for peak period to peak width conversion
static const uint16_t bark_tab_m44_512[]
int(* read_bitstream)(AVCodecContext *avctx, struct TwinVQContext *tctx, const uint8_t *buf, int buf_size)
int channels
number of audio channels
#define TWINVQ_SUB_GAIN_BITS
static const uint16_t bark_tab_l44_2048[]
uint8_t pi<< 24) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_U8, uint8_t,(*(const uint8_t *) pi - 0x80) *(1.0f/(1<< 7))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_U8, uint8_t,(*(const uint8_t *) pi - 0x80) *(1.0/(1<< 7))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S16, int16_t,(*(const int16_t *) pi >> 8)+0x80) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S16, int16_t, *(const int16_t *) pi *(1.0f/(1<< 15))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S16, int16_t, *(const int16_t *) pi *(1.0/(1<< 15))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S32, int32_t,(*(const int32_t *) pi >> 24)+0x80) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S32, int32_t, *(const int32_t *) pi *(1.0f/(1U<< 31))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S32, int32_t, *(const int32_t *) pi *(1.0/(1U<< 31))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_FLT, float, av_clip_uint8(lrintf(*(const float *) pi *(1<< 7))+0x80)) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_FLT, float, av_clip_int16(lrintf(*(const float *) pi *(1<< 15)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_FLT, float, av_clipl_int32(llrintf(*(const float *) pi *(1U<< 31)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_DBL, double, av_clip_uint8(lrint(*(const double *) pi *(1<< 7))+0x80)) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_DBL, double, av_clip_int16(lrint(*(const double *) pi *(1<< 15)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_DBL, double, av_clipl_int32(llrint(*(const double *) pi *(1U<< 31)))) #define SET_CONV_FUNC_GROUP(ofmt, ifmt) static void set_generic_function(AudioConvert *ac) { } void ff_audio_convert_free(AudioConvert **ac) { if(! *ac) return;ff_dither_free(&(*ac) ->dc);av_freep(ac);} AudioConvert *ff_audio_convert_alloc(AVAudioResampleContext *avr, enum AVSampleFormat out_fmt, enum AVSampleFormat in_fmt, int channels, int sample_rate, int apply_map) { AudioConvert *ac;int in_planar, out_planar;ac=av_mallocz(sizeof(*ac));if(!ac) return NULL;ac->avr=avr;ac->out_fmt=out_fmt;ac->in_fmt=in_fmt;ac->channels=channels;ac->apply_map=apply_map;if(avr->dither_method !=AV_RESAMPLE_DITHER_NONE &&av_get_packed_sample_fmt(out_fmt)==AV_SAMPLE_FMT_S16 &&av_get_bytes_per_sample(in_fmt) > 2) { ac->dc=ff_dither_alloc(avr, out_fmt, in_fmt, channels, sample_rate, apply_map);if(!ac->dc) { av_free(ac);return NULL;} return ac;} in_planar=ff_sample_fmt_is_planar(in_fmt, channels);out_planar=ff_sample_fmt_is_planar(out_fmt, channels);if(in_planar==out_planar) { ac->func_type=CONV_FUNC_TYPE_FLAT;ac->planes=in_planar ? ac->channels :1;} else if(in_planar) ac->func_type=CONV_FUNC_TYPE_INTERLEAVE;else ac->func_type=CONV_FUNC_TYPE_DEINTERLEAVE;set_generic_function(ac);if(ARCH_AARCH64) ff_audio_convert_init_aarch64(ac);if(ARCH_ARM) ff_audio_convert_init_arm(ac);if(ARCH_X86) ff_audio_convert_init_x86(ac);return ac;} int ff_audio_convert(AudioConvert *ac, AudioData *out, AudioData *in) { int use_generic=1;int len=in->nb_samples;int p;if(ac->dc) { av_log(ac->avr, AV_LOG_TRACE, "%d samples - audio_convert: %s to %s (dithered)\n", len, av_get_sample_fmt_name(ac->in_fmt), av_get_sample_fmt_name(ac->out_fmt));return ff_convert_dither(ac-> in
static const uint16_t bark_tab_m08_256[]
uint8_t * extradata
some codecs need / can use extradata like Huffman tables.
float bark_hist[3][2][40]
BSE coefficients of last frame.
AVSampleFormat
Audio sample formats.
const char * name
Name of the codec implementation.
static const TwinVQModeTab mode_22_32
int block_align
number of bytes per packet if constant and known or 0 Used by some WAV based audio codecs.
main external API structure.
static const uint16_t bark_tab_l22_512[]
static const TwinVQModeTab mode_22_20
static const uint16_t bark_tab_s22_128[]
static const TwinVQModeTab mode_44_40
static const uint16_t bark_tab_m11_256[]
static void dec_bark_env(TwinVQContext *tctx, const uint8_t *in, int use_hist, int ch, float *out, float gain, enum TwinVQFrameType ftype)
static const uint16_t bark_tab_m22_512[]
AVCodec ff_twinvq_decoder
static const uint16_t bark_tab_l11_512[]
#define AVERROR_INVALIDDATA
Invalid data found when processing input.
static void read_cb_data(TwinVQContext *tctx, GetBitContext *gb, uint8_t *dst, enum TwinVQFrameType ftype)
static const uint16_t bark_tab_l22_1024[]
uint8_t lsp_split
number of CB entries for the LSP decoding
enum TwinVQFrameType ff_twinvq_wtype_to_ftype_table[]
static const uint16_t bark_tab_s08_64[]
struct TwinVQFrameMode fmode[3]
frame type-dependent parameters
uint8_t bark_env_size
number of distinct bark scale envelope values