31 #define BITSTREAM_READER_LE 43 float ppc_gain,
float *speech,
int len)
46 const float *shape_end = shape +
len;
49 for (i = 0; i < width / 2; i++)
50 speech[i] += ppc_gain * *shape++;
53 center = (
int)(i * period + 0.5);
54 for (j = -width / 2; j < (width + 1) / 2; j++)
55 speech[j + center] += ppc_gain * *shape++;
59 center = (
int)(i * period + 0.5);
60 for (j = -width / 2; j < (width + 1) / 2 && shape < shape_end; j++)
61 speech[j + center] += ppc_gain * *shape++;
65 const float *shape,
float *speech)
72 float ratio = (float)mtab->
size / isampf;
73 float min_period, max_period, period_range,
period;
76 float pgain_base, pgain_step, ppc_gain;
79 min_period =
log2(ratio * 0.2);
80 max_period = min_period +
log2(6);
82 min_period = (
int)(ratio * 0.2 * 400 + 0.5) / 400.0;
83 max_period = (
int)(ratio * 0.2 * 400 * 6 + 0.5) / 400.0;
85 period_range = max_period - min_period;
86 period = min_period + period_coef * period_range /
94 case 8: some_mult = 2.0;
break;
95 case 11: some_mult = 3.0;
break;
96 case 16: some_mult = 3.0;
break;
97 case 22: some_mult = ibps == 32 ? 2.0 : 4.0;
break;
98 case 44: some_mult = 8.0;
break;
99 default: some_mult = 4.0;
103 if (isampf == 22 && ibps == 32)
104 width = (
int)((2.0 /
period + 1) * width + 0.5);
107 pgain_step = pgain_base / ((1 << mtab->
pgain_bit) - 1);
108 ppc_gain = 1.0 / 8192 *
116 int ch,
float *
out,
float gain,
121 float *hist = tctx->
bark_hist[ftype][ch];
122 float val = ((
const float []) { 0.4, 0.35, 0.28 })[ftype];
129 for (i = 0; i < fw_cb_len; i++)
130 for (j = 0; j < bark_n_coef; j++, idx++) {
131 float tmp2 = mtab->
fmode[ftype].
bark_cb[fw_cb_len * in[j] +
i] *
137 tmp2 + val * hist[idx] + 1.0 : tmp2 + 1.0;
139 st = use_hist ? (1.0 -
val) * tmp2 + val * hist[idx] + 1.0
157 for (i = 0; i < tctx->
n_div[ftype]; i++) {
166 const uint8_t *buf,
int buf_size)
199 for (j = 0; j <
sub; j++)
201 bits->
bark1[i][j][k] =
205 for (j = 0; j <
sub; j++)
214 for (j = 0; j <
sub; j++)
252 {
MKTAG(
'V',
'X',
'0',
'3'), 6, 1, 8000 },
253 {
MKTAG(
'V',
'X',
'0',
'4'), 12, 2, 8000 },
255 {
MKTAG(
'V',
'O',
'X',
'i'), 8, 1, 8000 },
256 {
MKTAG(
'V',
'O',
'X',
'j'), 10, 1, 11025 },
257 {
MKTAG(
'V',
'O',
'X',
'k'), 16, 1, 16000 },
258 {
MKTAG(
'V',
'O',
'X',
'L'), 24, 1, 22050 },
259 {
MKTAG(
'V',
'O',
'X',
'q'), 32, 1, 44100 },
260 {
MKTAG(
'V',
'O',
'X',
'r'), 40, 1, 44100 },
261 {
MKTAG(
'V',
'O',
'X',
's'), 48, 1, 44100 },
262 {
MKTAG(
'V',
'O',
'X',
't'), 16, 2, 8000 },
263 {
MKTAG(
'V',
'O',
'X',
'u'), 20, 2, 11025 },
264 {
MKTAG(
'V',
'O',
'X',
'v'), 32, 2, 16000 },
265 {
MKTAG(
'V',
'O',
'X',
'w'), 48, 2, 22050 },
266 {
MKTAG(
'V',
'O',
'X',
'x'), 64, 2, 44100 },
267 {
MKTAG(
'V',
'O',
'X',
'y'), 80, 2, 44100 },
268 {
MKTAG(
'V',
'O',
'X',
'z'), 96, 2, 44100 },
292 if (props->
tag == tag) {
312 switch ((avctx->
channels << 16) + (isampf << 8) + ibps) {
313 case (1 << 16) + ( 8 << 8) + 6:
316 case (2 << 16) + ( 8 << 8) + 6:
319 case (1 << 16) + ( 8 << 8) + 8:
322 case (2 << 16) + ( 8 << 8) + 8:
325 case (1 << 16) + (11 << 8) + 10:
328 case (2 << 16) + (11 << 8) + 10:
331 case (1 << 16) + (16 << 8) + 16:
334 case (2 << 16) + (16 << 8) + 16:
337 case (1 << 16) + (22 << 8) + 24:
340 case (2 << 16) + (22 << 8) + 24:
343 case (1 << 16) + (44 << 8) + 32:
344 case (2 << 16) + (44 << 8) + 32:
347 case (1 << 16) + (44 << 8) + 40:
348 case (2 << 16) + (44 << 8) + 40:
351 case (1 << 16) + (44 << 8) + 48:
352 case (2 << 16) + (44 << 8) + 48:
357 "This version does not support %d kHz - %d kbit/s/ch mode.\n",
#define AVERROR_INVALIDDATA
Invalid data found when processing input.
uint8_t bark_n_bit
number of bits of the BSE coefs
uint8_t ppc_coeffs[TWINVQ_PPC_SHAPE_LEN_MAX]
int bits_main_spec_change[4]
static unsigned int get_bits(GetBitContext *s, int n)
Read 1-25 bits.
const TwinVQModeTab * mtab
int64_t bit_rate
the average bitrate
TwinVQFrameData bits[TWINVQ_MAX_FRAMES_PER_PACKET]
int p_coef[TWINVQ_CHANNELS_MAX]
static av_cold int init(AVCodecContext *avctx)
uint8_t bark_n_coef
number of BSE CB coefficients to read
uint16_t size
frame size in samples
#define AV_CODEC_CAP_CHANNEL_CONF
Codec should fill in channel configuration and samplerate instead of container.
#define AV_CH_LAYOUT_STEREO
uint8_t bark_use_hist[TWINVQ_CHANNELS_MAX][TWINVQ_SUBBLOCKS_MAX]
uint8_t lpc_idx1[TWINVQ_CHANNELS_MAX]
static void decode(AVCodecContext *dec_ctx, AVPacket *pkt, AVFrame *frame, FILE *outfile)
enum TwinVQFrameType ff_twinvq_wtype_to_ftype_table[]
uint8_t sub_gain_bits[TWINVQ_CHANNELS_MAX *TWINVQ_SUBBLOCKS_MAX]
Short frame (divided in n sub-blocks)
void(* decode_ppc)(struct TwinVQContext *tctx, int period_coef, int g_coef, const float *shape, float *speech)
uint8_t lpc_idx2[TWINVQ_CHANNELS_MAX][TWINVQ_LSP_SPLIT_MAX]
int g_coef[TWINVQ_CHANNELS_MAX]
uint8_t ppc_period_bit
number of the bits for the PPC period value
av_cold int ff_twinvq_decode_close(AVCodecContext *avctx)
uint8_t gain_bits[TWINVQ_CHANNELS_MAX]
uint8_t * extradata
some codecs need / can use extradata like Huffman tables.
static int get_bits_count(const GetBitContext *s)
#define TWINVQ_WINDOW_TYPE_BITS
Parameters and tables that are different for every combination of bitrate/sample rate.
uint8_t lpc_hist_idx[TWINVQ_CHANNELS_MAX]
bitstream reader API header.
Long frame (single sub-block + PPC)
uint8_t bark_env_size
number of distinct bark scale envelope values
#define ROUNDED_DIV(a, b)
static float twinvq_mulawinv(float y, float clip, float mu)
uint8_t main_coeffs[1024]
#define AV_LOG_ERROR
Something went wrong and cannot losslessly be recovered.
#define NULL_IF_CONFIG_SMALL(x)
Return NULL if CONFIG_SMALL is true, otherwise the argument without modification. ...
const char * name
Name of the codec implementation.
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
uint64_t channel_layout
Audio channel layout.
audio channel layout utility functions
uint8_t sub
Number subblocks in each frame.
uint8_t bits_main_spec[2][4][2]
bits for the main codebook
static void twinvq_memset_float(float *buf, float val, int size)
int ff_twinvq_decode_frame(AVCodecContext *avctx, void *data, int *got_frame_ptr, AVPacket *avpkt)
int(* read_bitstream)(AVCodecContext *avctx, struct TwinVQContext *tctx, const uint8_t *buf, int buf_size)
Libavcodec external API header.
AVSampleFormat
Audio sample formats.
float bark_hist[3][2][40]
BSE coefficients of last frame.
int sample_rate
samples per second
static int init_get_bits8(GetBitContext *s, const uint8_t *buffer, int byte_size)
Initialize GetBitContext.
main external API structure.
const uint16_t * bark_tab
enum TwinVQFrameType ftype
const int16_t * bark_cb
codebook for the bark scale envelope (BSE)
static unsigned int get_bits1(GetBitContext *s)
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 void skip_bits(GetBitContext *s, int n)
struct TwinVQFrameMode fmode[3]
frame type-dependent parameters
uint8_t pgain_bit
bits for PPC gain
common internal api header.
uint8_t ppc_shape_len
size of PPC shape CB
#define TWINVQ_SUB_GAIN_BITS
void(* dec_bark_env)(struct TwinVQContext *tctx, const uint8_t *in, int use_hist, int ch, float *out, float gain, enum TwinVQFrameType ftype)
int channels
number of audio channels
static enum AVSampleFormat sample_fmts[]
static float sub(float src0, float src1)
#define TWINVQ_CHANNELS_MAX
Filter the word “frame” indicates either a video frame or a group of audio as stored in an AVFrame structure Format for each input and each output the list of supported formats For video that means pixel format For audio that means channel sample they are references to shared objects When the negotiation mechanism computes the intersection of the formats supported at each end of a all references to both lists are replaced with a reference to the intersection And when a single format is eventually chosen for a link amongst the remaining all references to the list are updated That means that if a filter requires that its input and output have the same format amongst a supported all it has to do is use a reference to the same list of formats query_formats can leave some formats unset and return AVERROR(EAGAIN) to cause the negotiation mechanism toagain later.That can be used by filters with complex requirements to use the format negotiated on one link to set the formats supported on another.Frame references ownership and permissions
#define AV_CH_LAYOUT_MONO
#define MKTAG(a, b, c, d)
uint64_t_TMPL AV_WL64 unsigned int_TMPL AV_RL32
static double val(void *priv, double ch)
#define AV_CODEC_CAP_DR1
Codec uses get_buffer() for allocating buffers and supports custom allocators.
uint8_t lsp_split
number of CB entries for the LSP decoding
uint8_t bark1[TWINVQ_CHANNELS_MAX][TWINVQ_SUBBLOCKS_MAX][TWINVQ_BARK_N_COEF_MAX]
av_cold int ff_twinvq_decode_init(AVCodecContext *avctx)