hoo2/Multimedia_AAC_Project
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Level 3: First positive SNR version

Browse Source
This commit is contained in:
hoo2
2026-02-15 21:16:54 +02:00
parent 4ebee28e4e
commit cd2b89bd73
28 changed files with 5043 additions and 275 deletions
Download Patch File Download Diff File Expand all files Collapse all files
source/level_1/core/aac_coder.py
+62 -41
View File
@@ -214,7 +214,10 @@ def aac_pack_frame_f_to_seq_channels(frame_type: FrameType, frame_f: FrameF) ->
# Level 1 encoder
# -----------------------------------------------------------------------------
def aac_coder_1(filename_in: Union[str, Path]) -> AACSeq1:
def aac_coder_1(
filename_in: Union[str, Path],
verbose: bool = False
) -> AACSeq1:
"""
Level-1 AAC encoder.
@@ -231,6 +234,8 @@ def aac_coder_1(filename_in: Union[str, Path]) -> AACSeq1:
filename_in : Union[str, Path]
Input WAV filename.
Assumption: stereo audio, sampling rate 48 kHz.
verbose : bool
Optional argument to print encoding status
Returns
-------
@@ -257,8 +262,8 @@ def aac_coder_1(filename_in: Union[str, Path]) -> AACSeq1:
aac_seq: AACSeq1 = []
prev_frame_type: FrameType = "OLS"
win_type: WinType = WIN_TYPE
if verbose:
print("Encoding ", end="", flush=True)
for i in range(K):
start = i * hop
@@ -275,23 +280,31 @@ def aac_coder_1(filename_in: Union[str, Path]) -> AACSeq1:
next_t = np.vstack([next_t, tail])
frame_type = aac_ssc(frame_t, next_t, prev_frame_type)
frame_f = aac_filter_bank(frame_t, frame_type, win_type)
frame_f = aac_filter_bank(frame_t, frame_type, WIN_TYPE)
chl_f, chr_f = aac_pack_frame_f_to_seq_channels(frame_type, frame_f)
aac_seq.append({
"frame_type": frame_type,
"win_type": win_type,
"win_type": WIN_TYPE,
"chl": {"frame_F": chl_f},
"chr": {"frame_F": chr_f},
})
prev_frame_type = frame_type
if verbose and (i % (K//20)) == 0:
print(".", end="", flush=True)
if verbose:
print(" done")
return aac_seq
def aac_coder_2(filename_in: Union[str, Path]) -> AACSeq2:
def aac_coder_2(
filename_in: Union[str, Path],
verbose: bool = False
) -> AACSeq2:
"""
Level-2 AAC encoder (Level 1 + TNS).
@@ -299,6 +312,8 @@ def aac_coder_2(filename_in: Union[str, Path]) -> AACSeq2:
----------
filename_in : Union[str, Path]
Input WAV filename (stereo, 48 kHz).
verbose : bool
Optional argument to print encoding status
Returns
-------
@@ -330,6 +345,8 @@ def aac_coder_2(filename_in: Union[str, Path]) -> AACSeq2:
aac_seq: AACSeq2 = []
prev_frame_type: FrameType = "OLS"
if verbose:
print("Encoding ", end="", flush=True)
for i in range(K):
start = i * hop
@@ -347,16 +364,7 @@ def aac_coder_2(filename_in: Union[str, Path]) -> AACSeq2:
# Level 1 analysis (packed stereo container)
frame_f_stereo = aac_filter_bank(frame_t, frame_type, WIN_TYPE)
# Unpack to per-channel (as you already do in Level 1)
if frame_type == "ESH":
chl_f = np.empty((128, 8), dtype=np.float64)
chr_f = np.empty((128, 8), dtype=np.float64)
for j in range(8):
chl_f[:, j] = frame_f_stereo[:, 2 * j + 0]
chr_f[:, j] = frame_f_stereo[:, 2 * j + 1]
else:
chl_f = frame_f_stereo[:, 0:1].astype(np.float64, copy=False)
chr_f = frame_f_stereo[:, 1:2].astype(np.float64, copy=False)
chl_f, chr_f = aac_pack_frame_f_to_seq_channels(frame_type, frame_f_stereo)
# Level 2: apply TNS per channel
chl_f_tns, chl_tns_coeffs = aac_tns(chl_f, frame_type)
@@ -370,8 +378,12 @@ def aac_coder_2(filename_in: Union[str, Path]) -> AACSeq2:
"chr": {"frame_F": chr_f_tns, "tns_coeffs": chr_tns_coeffs},
}
)
prev_frame_type = frame_type
if verbose and (i % (K//20)) == 0:
print(".", end="", flush=True)
if verbose:
print(" done")
return aac_seq
@@ -379,6 +391,7 @@ def aac_coder_2(filename_in: Union[str, Path]) -> AACSeq2:
def aac_coder_3(
filename_in: Union[str, Path],
filename_aac_coded: Union[str, Path] | None = None,
verbose: bool = False,
) -> AACSeq3:
"""
Level-3 AAC encoder (Level 2 + Psycho + Quantizer + Huffman).
@@ -389,6 +402,8 @@ def aac_coder_3(
Input WAV filename (stereo, 48 kHz).
filename_aac_coded : Union[str, Path] | None
Optional .mat filename to store aac_seq_3 (assignment convenience).
verbose : bool
Optional argument to print encoding status
Returns
-------
@@ -416,15 +431,14 @@ def aac_coder_3(
aac_seq: AACSeq3 = []
prev_frame_type: FrameType = "OLS"
# Pin win_type to the WinType literal for type checkers.
win_type: WinType = WIN_TYPE
# Psycho model needs per-channel history (prev1, prev2) of 2048-sample frames.
prev1_L = np.zeros((2048,), dtype=np.float64)
prev2_L = np.zeros((2048,), dtype=np.float64)
prev1_R = np.zeros((2048,), dtype=np.float64)
prev2_R = np.zeros((2048,), dtype=np.float64)
if verbose:
print("Encoding ", end="", flush=True)
for i in range(K):
start = i * hop
@@ -440,7 +454,7 @@ def aac_coder_3(
frame_type = aac_ssc(frame_t, next_t, prev_frame_type)
# Analysis filterbank (stereo packed)
frame_f_stereo = aac_filter_bank(frame_t, frame_type, win_type)
frame_f_stereo = aac_filter_bank(frame_t, frame_type, WIN_TYPE)
chl_f, chr_f = aac_pack_frame_f_to_seq_channels(frame_type, frame_f_stereo)
# TNS per channel
@@ -474,32 +488,35 @@ def aac_coder_3(
# Codebook 11:
# maxAbsCodeVal = 16 is RESERVED for ESCAPE.
# We must stay strictly within [-15, +15] to avoid escape decoding.
sf_cb = 11
sf_max_abs = int(huff_LUT_list[sf_cb]["maxAbsCodeVal"]) - 1 # -> 15
# sf_cb = 11
# sf_max_abs = int(huff_LUT_list[sf_cb]["maxAbsCodeVal"]) - 1 # -> 15
#
# sfc_L_dpcm = np.clip(
# sfc_L_dpcm,
# -sf_max_abs,
# sf_max_abs,
# ).astype(np.int64, copy=False)
#
# sfc_R_dpcm = np.clip(
# sfc_R_dpcm,
# -sf_max_abs,
# sf_max_abs,
# ).astype(np.int64, copy=False)
sfc_L_dpcm = np.clip(
sfc_L_dpcm,
-sf_max_abs,
sf_max_abs,
).astype(np.int64, copy=False)
sfc_R_dpcm = np.clip(
sfc_R_dpcm,
-sf_max_abs,
sf_max_abs,
).astype(np.int64, copy=False)
sfc_L_stream, _ = aac_encode_huff(
sfc_L_stream, cb_sfc_L = aac_encode_huff(
sfc_L_dpcm.reshape(-1, order="F"),
huff_LUT_list,
force_codebook=sf_cb,
# force_codebook=11,
)
sfc_R_stream, _ = aac_encode_huff(
sfc_R_stream, cb_sfc_R = aac_encode_huff(
sfc_R_dpcm.reshape(-1, order="F"),
huff_LUT_list,
force_codebook=sf_cb,
# force_codebook=11,
)
if cb_sfc_L != 11 or cb_sfc_R != 11:
print (f"frame: {i}: cb_sfc_l={cb_sfc_L}, cb_sfc_r={cb_sfc_R}")
mdct_L_stream, cb_L = aac_encode_huff(
np.asarray(S_L, dtype=np.int64).reshape(-1),
huff_LUT_list,
@@ -512,7 +529,7 @@ def aac_coder_3(
# Typed dict construction helps static analyzers validate the schema.
frame_out: AACSeq3Frame = {
"frame_type": frame_type,
"win_type": win_type,
"win_type": WIN_TYPE,
"chl": {
"tns_coeffs": np.asarray(chl_tns_coeffs, dtype=np.float64),
"T": np.asarray(T_L, dtype=np.float64),
@@ -539,6 +556,11 @@ def aac_coder_3(
prev1_R = frame_R
prev_frame_type = frame_type
if verbose and (i % (K//20)) == 0:
print(".", end="", flush=True)
if verbose:
print(" done")
# Optional: store to .mat for the assignment wrapper
if filename_aac_coded is not None:
@@ -548,6 +570,5 @@ def aac_coder_3(
{"aac_seq_3": np.array(aac_seq, dtype=object)},
do_compression=True,
)
return aac_seq
source/level_1/core/aac_decoder.py
+41 -4
View File
@@ -118,7 +118,11 @@ def aac_remove_padding(y_pad: StereoSignal, hop: int = 1024) -> StereoSignal:
# Level 1 decoder
# -----------------------------------------------------------------------------
def aac_decoder_1(aac_seq_1: AACSeq1, filename_out: Union[str, Path]) -> StereoSignal:
def aac_decoder_1(
aac_seq_1: AACSeq1,
filename_out: Union[str, Path],
verbose: bool = False
) -> StereoSignal:
"""
Level-1 AAC decoder (inverse of aac_coder_1()).
@@ -134,6 +138,8 @@ def aac_decoder_1(aac_seq_1: AACSeq1, filename_out: Union[str, Path]) -> StereoS
Encoded sequence as produced by aac_coder_1().
filename_out : Union[str, Path]
Output WAV filename. Assumption: 48 kHz, stereo.
verbose : bool
Optional argument to print encoding status
Returns
-------
@@ -152,6 +158,8 @@ def aac_decoder_1(aac_seq_1: AACSeq1, filename_out: Union[str, Path]) -> StereoS
n_pad = (K - 1) * hop + win
y_pad: StereoSignal = np.zeros((n_pad, 2), dtype=np.float64)
if verbose:
print("Decoding ", end="", flush=True)
for i, fr in enumerate(aac_seq_1):
frame_type: FrameType = fr["frame_type"]
win_type: WinType = fr["win_type"]
@@ -164,12 +172,15 @@ def aac_decoder_1(aac_seq_1: AACSeq1, filename_out: Union[str, Path]) -> StereoS
start = i * hop
y_pad[start:start + win, :] += frame_t_hat
if verbose and (i % (K//20)) == 0:
print(".", end="", flush=True)
y: StereoSignal = aac_remove_padding(y_pad, hop=hop)
if verbose:
print(" done")
# Level 1 assumption: 48 kHz output.
sf.write(str(filename_out), y, 48000)
return y
@@ -177,7 +188,11 @@ def aac_decoder_1(aac_seq_1: AACSeq1, filename_out: Union[str, Path]) -> StereoS
# Level 2 decoder
# -----------------------------------------------------------------------------
def aac_decoder_2(aac_seq_2: AACSeq2, filename_out: Union[str, Path]) -> StereoSignal:
def aac_decoder_2(
aac_seq_2: AACSeq2,
filename_out: Union[str, Path],
verbose: bool = False
) -> StereoSignal:
"""
Level-2 AAC decoder (inverse of aac_coder_2).
@@ -195,6 +210,8 @@ def aac_decoder_2(aac_seq_2: AACSeq2, filename_out: Union[str, Path]) -> StereoS
Encoded sequence as produced by aac_coder_2().
filename_out : Union[str, Path]
Output WAV filename.
verbose : bool
Optional argument to print encoding status
Returns
-------
@@ -213,6 +230,8 @@ def aac_decoder_2(aac_seq_2: AACSeq2, filename_out: Union[str, Path]) -> StereoS
n_pad = (K - 1) * hop + win
y_pad = np.zeros((n_pad, 2), dtype=np.float64)
if verbose:
print("Decoding ", end="", flush=True)
for i, fr in enumerate(aac_seq_2):
frame_type: FrameType = fr["frame_type"]
win_type: WinType = fr["win_type"]
@@ -260,15 +279,23 @@ def aac_decoder_2(aac_seq_2: AACSeq2, filename_out: Union[str, Path]) -> StereoS
start = i * hop
y_pad[start : start + win, :] += frame_t_hat
if verbose and (i % (K//20)) == 0:
print(".", end="", flush=True)
y = aac_remove_padding(y_pad, hop=hop)
if verbose:
print(" done")
sf.write(str(filename_out), y, 48000)
return y
def aac_decoder_3(aac_seq_3: AACSeq3, filename_out: Union[str, Path]) -> StereoSignal:
def aac_decoder_3(
aac_seq_3: AACSeq3,
filename_out: Union[str, Path],
verbose: bool = False,
) -> StereoSignal:
"""
Level-3 AAC decoder (inverse of aac_coder_3).
@@ -286,6 +313,8 @@ def aac_decoder_3(aac_seq_3: AACSeq3, filename_out: Union[str, Path]) -> StereoS
Encoded sequence as produced by aac_coder_3.
filename_out : Union[str, Path]
Output WAV filename.
verbose : bool
Optional argument to print encoding status
Returns
-------
@@ -307,6 +336,9 @@ def aac_decoder_3(aac_seq_3: AACSeq3, filename_out: Union[str, Path]) -> StereoS
n_pad = (K - 1) * hop + win
y_pad = np.zeros((n_pad, 2), dtype=np.float64)
if verbose:
print("Decoding ", end="", flush=True)
for i, fr in enumerate(aac_seq_3):
frame_type: FrameType = fr["frame_type"]
win_type: WinType = fr["win_type"]
@@ -401,7 +433,12 @@ def aac_decoder_3(aac_seq_3: AACSeq3, filename_out: Union[str, Path]) -> StereoS
start = i * hop
y_pad[start : start + win, :] += frame_t_hat
if verbose and (i % (K//20)) == 0:
print(".", end="", flush=True)
y = aac_remove_padding(y_pad, hop=hop)
if verbose:
print(" done")
sf.write(str(filename_out), y, 48000)
return y
source/level_1/level_1.py
+3 -2
View File
@@ -20,6 +20,7 @@
from __future__ import annotations
from pathlib import Path
from tabnanny import verbose
from typing import Union
import soundfile as sf
@@ -52,7 +53,7 @@ def aac_coder_1(filename_in: Union[str, Path]) -> AACSeq1:
AACSeq1
List of encoded frames (Level 1 schema).
"""
return core_aac_coder_1(filename_in)
return core_aac_coder_1(filename_in, verbose=True)
def aac_decoder_1(aac_seq_1: AACSeq1, filename_out: Union[str, Path]) -> StereoSignal:
@@ -73,7 +74,7 @@ def aac_decoder_1(aac_seq_1: AACSeq1, filename_out: Union[str, Path]) -> StereoS
StereoSignal
Decoded audio samples (time-domain), stereo, shape (N, 2), dtype float64.
"""
return core_aac_decoder_1(aac_seq_1, filename_out)
return core_aac_decoder_1(aac_seq_1, filename_out, verbose=True)
# -----------------------------------------------------------------------------