Merge branch 'background_noise' into 'main' (b3e90d7c) · Commits · IVAS Codec Public Collaboration / IVAS Processing Scripts

examples/TEMPLATE.yml

+34 −20

Original line number	Diff line number	Diff line
		@@ -16,17 +16,15 @@
		# delete_tmp: true
		### Master seed for random processes like bitstream error pattern generation; default = 0
		# master_seed: 5
		### Additional seed to specify number of preruns; default = 0
		# prerun_seed: 2

		### Any relative paths will be interpreted relative to the working directory the script is called from!
		### Usage of absolute paths is recommended.
		### Do not use file names with dots "." in them! This is not supported, use "_" instead
		### For Windows user: please use double back slash '\\' in paths and add '.exe' to executable definitions
		### REQUIRED: Input path or file
		input_path: "~/ivas/items/HOA3"
		input_path: ".../ivas/items/HOA3"
		### REQUIRED: Output path or file
		output_path: "./tmp_output"
		output_path: ".../tmp_output"
		### Metadata path or file(s)
		### If input format is ISM{1-4} a path for the metadata files can be specified;
		### default = null (for ISM search for item_name.{wav, raw, pcm}.{0-3}.csv in input folder, otherise ignored)
		@@ -49,17 +47,6 @@ output_path: "./tmp_output"
		# input_select:
		# - "48kHz"

		### Horizontally concatenate input items into one long file; default = false
		# concatenate_input: true
		### Specify the concatenation order in a list of strings. If not specified, the concatenation order would be
		### as per the filesystem on the users' device
		### Should only be used if concatenate_input = true
		# concatenation_order: []
		### Specify preamble duration in ms; default = 0
		# preamble: 40
		### Flag wheter to use noise (amplitude +-4) for the preamble or silence; default = false (silence)
		# pad_noise_preamble: true

		################################################
		### Input configuration
		################################################
		@@ -70,7 +57,7 @@ input:
		# fs: 32000

		################################################
		### Pre-processing
		### Pre-processing on individual items
		################################################
		### Pre-processing step performed prior to core processing for all conditions
		### If not defined, preprocessing step is skipped
		@@ -97,6 +84,31 @@ input:
		### Length of window used at start/end of signal (ms); default = 0
		# window: 100

		################################################
		### Pre-processing on whole signal(s)
		################################################
		# preprocessing_2:
		### Options for processing of the concatenated item (concatenate_input: true) or
		### the individual items (concatenate_input: false) after previous pre-processing step
		### Horizontally concatenate input items into one long file; default = false
		# concatenate_input: true
		### Specify the concatenation order in a list of strings. If not specified, the concatenation order would be
		### as per the filesystem on the users' device
		### Should only be used if concatenate_input = true
		# concatenation_order: []
		### Specify preamble duration in ms; default = 0
		# preamble: 10000
		### Flag wheter to use noise (amplitude +-4) for the preamble or silence; default = false (silence)
		# preamble_noise: true
		### Additive background noise
		# background_noise:
		### REQUIRED: SNR for background noise in dB
		# snr: 10
		### REQUIRED: Path to background noise
		# background_noise_path: ".../noise.wav"
		### Seed for delay offest; default = 0
		# seed_delay: 10

		#################################################
		### Bitstream processing
		#################################################
		@@ -122,6 +134,8 @@ input:
		# error_pattern: "path/pattern.192"
		### Error rate in percent
		# error_rate: 5
		### Additional seed to specify number of preruns; default = 0
		# prerun_seed: 2

		################################################
		### Configuration for conditions under test
		@@ -209,7 +223,7 @@ conditions_to_generate:
		### Path to decoder binary; default search for IVAS_dec in bin folder (primary) and PATH (secondary)
		bin: ~/git/ivas-codec/IVAS_dec
		### Decoder output format; default = postprocessing fmt
		fmt: "CICP19"
		fmt: "7_1_4"
		### Decoder output sampling rate; default = null (same as input)
		# fs: 48000
		### Additional commandline options; default = null
		@@ -244,8 +258,8 @@ conditions_to_generate:
		postprocessing:
		### REQUIRED: Target format for output
		fmt: "BINAURAL"
		### Target sampling rate in Hz for resampling; default = null (no resampling)
		# fs: 16000
		### REQUIRED: Target sampling rate in Hz for resampling
		fs: 48000
		### Low-pass cut-off frequency in Hz; default = null (no filtering)
		# lp_cutoff: 24000
		### Target loudness in LKFS; default = null (no loudness change applied)

ivas_processing_scripts/init.py

+20 −27

Original line number	Diff line number	Diff line
		@@ -36,7 +36,6 @@ from itertools import repeat
		import yaml

		from ivas_processing_scripts.audiotools.metadata import check_ISM_metadata
		from ivas_processing_scripts.audiotools.wrappers.bs1770 import scale_files
		from ivas_processing_scripts.constants import (
		LOGGER_DATEFMT,
		LOGGER_FORMAT,
		@@ -44,11 +43,11 @@ from ivas_processing_scripts.constants import (
		)
		from ivas_processing_scripts.processing import chains, config
		from ivas_processing_scripts.processing.processing import (
		concat_setup,
		concat_teardown,
		preprocess,
		preprocess_2,
		process_item,
		reorder_items_list,
		reverse_process_2,
		)
		from ivas_processing_scripts.utils import DirManager, apply_func_parallel

		@@ -95,8 +94,15 @@ def main(args):
		logger = logging_init(args, cfg)

		# Re-ordering items based on concatenation order
		if cfg.concatenate_input and cfg.concatenation_order is not None:
		cfg.items_list = reorder_items_list(cfg.items_list, cfg.concatenation_order)
		if hasattr(cfg, "preprocessing_2"):
		if (
		cfg.preprocessing_2.get("concatenate_input")
		and cfg.preprocessing_2.get("concatenation_order", None) is not None
		):
		cfg.items_list = reorder_items_list(
		cfg.items_list, cfg.preprocessing_2["concatenation_order"]
		)

		# check for ISM metadata
		if cfg.input["fmt"].startswith("ISM"):
		metadata = check_ISM_metadata(
		@@ -121,12 +127,15 @@ def main(args):

		# run preprocessing only once
		if hasattr(cfg, "preprocessing"):
		preprocess(cfg, cfg.metadata_path, logger)
		preprocess(cfg, logger)

		if cfg.concatenate_input:
		# concatenate items if required
		concat_setup(cfg, logger)
		# preprocessing on whole signal(s)
		if hasattr(cfg, "preprocessing_2"):
		# save process info to revert it later
		cfg.pre2 = cfg.proc_chains[0]["processes"][0]
		preprocess_2(cfg, logger)

		# run conditions
		for condition, out_dir, tmp_dir in zip(
		cfg.proc_chains, cfg.out_dirs, cfg.tmp_dirs
		):
		@@ -134,11 +143,6 @@ def main(args):

		logger.info(f" Generating condition: {condition['name']}")

		# # TODO: what happens when no concatenation or only one file for concatenation?
		# if condition["processes"][0].name == "ivas": # TODO: check if 0 index sufficient
		# a = {"number_frames": cfg.num_frames, "number_frames_preamble": cfg.num_frames_preamble}
		# condition["processes"][0].tx.update(a)

		apply_func_parallel(
		process_item,
		zip(
		@@ -153,19 +157,8 @@ def main(args):
		"mp" if cfg.multiprocessing else None,
		)

		if cfg.concatenate_input:
		# write out the splits, optionally remove file
		out_paths_splits, out_meta_splits = concat_teardown(cfg, logger)
		# scale individual files
		if cfg.postprocessing.get("loudness", False):
		# TODO: take care of samplingrate
		scale_files(
		out_paths_splits,
		cfg.postprocessing["fmt"],
		cfg.postprocessing["loudness"],
		cfg.postprocessing.get("fs", None),
		out_meta_splits,
		)
		if hasattr(cfg, "preprocessing_2"):
		reverse_process_2(cfg, logger)

		# copy configuration to output directory
		with open(cfg.output_path.joinpath(f"{cfg.name}.yml"), "w") as f:

ivas_processing_scripts/audiotools/audiofile.py

+2 −2

Original line number	Diff line number	Diff line
		@@ -150,8 +150,8 @@ def write(
		def concat(
		in_filenames: list,
		out_file: str,
		silence_pre: int,
		silence_post: int,
		silence_pre: Optional[int] = 0,
		silence_post: Optional[int] = 0,
		in_fs: Optional[int] = 48000,
		num_channels: Optional[int] = None,
		pad_noise: Optional[bool] = False,

ivas_processing_scripts/audiotools/metadata.py

+43 −30

Original line number	Diff line number	Diff line
		@@ -188,7 +188,7 @@ def write_ISM_metadata_in_file(
		List of acutally used file names
		"""

		if len(metadata) != len(file_name) and not automatic_naming:
		if not automatic_naming and len(metadata) != len(file_name):
		raise ValueError("Number of metadata objects and file names has to match")
		number_objects = len(metadata)

		@@ -299,9 +299,9 @@ def concat_meta_from_file(
		audio_files: list[str],
		meta_files: list[list[str]],
		out_file: list[str],
		silence_pre: int,
		silence_post: int,
		input_fmt: str,
		silence_pre: Optional[int] = 0,
		silence_post: Optional[int] = 0,
		preamble: Optional[int] = None,
		) -> None:
		"""
		@@ -315,12 +315,12 @@ def concat_meta_from_file(
		List of corresponding metadata file names
		out_file: list[str]
		Name of concatenated output file
		silence_pre: int
		Silence inserted before each item
		silence_post: int
		Silence inserted after each item
		input_fmt: str
		Input audio format
		silence_pre: Optional[int]
		Silence inserted before each item
		silence_post: Optional[int]
		Silence inserted after each item
		preamble: Optional[int]
		Length of preamble in milliseconds
		"""
		@@ -362,7 +362,7 @@ def concat_meta_from_file(
		# pad
		trim_meta(
		audio_item, (-silence_pre, -silence_post)
		) # use negative value since we wante to pad, not trim
		) # use negative value since we want to pad, not trim

		# concatenate
		for idx, obj_pos in enumerate(audio_item.object_pos):
		@@ -374,26 +374,7 @@ def concat_meta_from_file(

		# add preamble
		if preamble:
		preamble_frames = preamble / IVAS_FRAME_LEN_MS
		if not preamble_frames.is_integer():
		raise ValueError(
		f"ISM metadata padding and trimming only possible if pad/trim length is multiple of frame length. "
		f"Frame length: {IVAS_FRAME_LEN_MS}ms"
		)
		for obj_idx in range(len(concat_meta_all_obj)):
		if (
		concat_meta_all_obj is not None
		and concat_meta_all_obj[obj_idx] is not None
		):
		concat_meta_all_obj[obj_idx] = trim(
		concat_meta_all_obj[obj_idx],
		limits=(-int(preamble_frames), 0),
		samples=True,
		)

		# add radius 1
		concat_meta_all_obj[obj_idx][: int(preamble_frames), 2] = 1
		pass
		concat_meta_all_obj = add_remove_preamble(concat_meta_all_obj, preamble)

		write_ISM_metadata_in_file(concat_meta_all_obj, out_file)

		@@ -529,7 +510,7 @@ def check_ISM_metadata(


		def metadata_search(
		in_meta: Union[str, Path],
		in_meta_path: Union[str, Path],
		item_names: list[Union[str, Path]],
		num_objects: int,
		) -> list[list[Union[Path, str]]]:
		@@ -542,7 +523,7 @@ def metadata_search(
		for item in item_names:
		list_item = []
		for obj_idx in range(num_objects):
		file_name_meta = in_meta / Path(item.stem).with_suffix(
		file_name_meta = in_meta_path / Path(item.stem).with_suffix(
		f"{item.suffix}.{obj_idx}.csv"
		)
		# check if file exists and add to list
		@@ -556,3 +537,35 @@ def metadata_search(
		list_meta.append(list_item)

		return list_meta


		def add_remove_preamble(
		metadata,
		preamble,
		add: Optional[bool] = True,
		):
		preamble_frames = preamble / IVAS_FRAME_LEN_MS
		if not preamble_frames.is_integer():
		raise ValueError(
		f"Application of preamble for ISM metadata is only possible if preamble length is multiple of frame length. "
		f"Frame length: {IVAS_FRAME_LEN_MS}ms"
		)
		for obj_idx in range(len(metadata)):
		if metadata is not None and metadata[obj_idx] is not None:
		if add:
		metadata[obj_idx] = trim(
		metadata[obj_idx],
		limits=(-int(preamble_frames), 0),
		samples=True,
		)

		# add radius 1
		metadata[obj_idx][: int(preamble_frames), 2] = 1
		else:
		metadata[obj_idx] = trim(
		metadata[obj_idx],
		limits=(int(preamble_frames), 0),
		samples=True,
		)

		return metadata

ivas_processing_scripts/audiotools/wrappers/gen_patt.py

+1 −1

Original line number	Diff line number	Diff line
		@@ -131,7 +131,7 @@ def create_error_pattern(
		tmp_sta_file = tmp_dir.joinpath("sta")

		# compute seed
		seed = random_seed(master_seed, prerun_seed)
		seed = random_seed((0, 99999999), master_seed, prerun_seed)

		# open file and modify
		lines = []