Make SOFA room processing optional and self-contained
SOFA and explicit .jochrtf inputs now render direct sound by default. --sofa-room enables the project image-source/FDN room, with the compact preset for Near/Mid and the original large room for Far. - preserve native HRIR timing and apply Data.Delay once - remove external reference configuration, radial head synthesis and the artificial centre response - ship both generated float64 room assets and their generator - retain .jochrtf as an explicit lightweight input and offline export - keep personalized headphone processing unchanged and update bilingual documentation Checked: independent direct/reflection convolution, FDN FIR/recursive agreement, fractional delay and metadata timing, chunk invariance, 8 bit-exact personalized regressions, CLI smoke tests, and full-song D1/D2 renders of two tracks.
This commit is contained in:
1 parent
26e84569c2
commit
3ea285e407
19 files changed
+861
-1134
No files matched your search
@@ -0,0 +1,123 @@
|
||||
"""Full-resolution coupling to the existing project-owned early/late room."""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import asdict
|
||||
import hashlib
|
||||
import json
|
||||
import math
|
||||
from pathlib import Path
|
||||
|
||||
import numpy as np
|
||||
from scipy import fft
|
||||
|
||||
from generate_sofa_room import SCHEMA, ROOM_PATHS
|
||||
from partitioned_convolution import UniformPartitionedConvolver
|
||||
from public_room import ShoeboxRoomConfig, first_order_image_sources
|
||||
from reference_distance import DistanceState, ReferenceDistanceProfileV1
|
||||
|
||||
|
||||
class SofaRoom:
|
||||
batch_samples = 1536
|
||||
|
||||
def __init__(self, source_count, reference, *, implementation_latency, recording_origin,
|
||||
path=None, preset=None):
|
||||
self.reference = reference
|
||||
self.preset = ("legacy" if reference.mode == "far" else "compact") if preset is None else str(preset)
|
||||
if self.preset not in ROOM_PATHS:
|
||||
raise ValueError("room preset must be compact or legacy")
|
||||
self.path = Path(ROOM_PATHS[self.preset] if path is None else path)
|
||||
with np.load(self.path, allow_pickle=False) as data:
|
||||
if str(data["schema"]) != SCHEMA or int(data["sample_rate_hz"]) != 48000:
|
||||
raise ValueError("unsupported SOFA room asset schema or sample rate")
|
||||
kernel = np.asarray(data["late_fir"], dtype="<f8")
|
||||
self.metadata = json.loads(str(data["metadata_json"]))
|
||||
if (kernel.ndim != 2 or kernel.shape[0] != 2 or kernel.shape[1] < 1
|
||||
or not np.isfinite(kernel).all()
|
||||
or hashlib.sha256(kernel.tobytes()).hexdigest() != self.metadata["kernel_sha256"]):
|
||||
raise ValueError("invalid SOFA room FIR or checksum")
|
||||
self.config = ShoeboxRoomConfig(**self.metadata["early_config"])
|
||||
self.config.validate()
|
||||
self.alignment_samples = int(implementation_latency) + max(0, int(recording_origin))
|
||||
kernel = np.pad(kernel, ((0, 0), (self.alignment_samples, 0)))
|
||||
self.convolver = UniformPartitionedConvolver(kernel, block_size=self.batch_samples)
|
||||
self.current = np.zeros(int(source_count))
|
||||
self.target = self.current.copy()
|
||||
self.pending_mono, self.pending_direct = [], []
|
||||
self.maximum_early_delay_samples = 0.
|
||||
|
||||
def distance_state(self, state):
|
||||
return DistanceState(
|
||||
self.reference.mode, state.normalized_radius, self.reference.reference_distance_m,
|
||||
max(ReferenceDistanceProfileV1.MINIMUM_DISTANCE_M, state.distance_m),
|
||||
state.direction[[1, 0, 2]] * [-1, 1, 1])
|
||||
|
||||
def paths(self, state):
|
||||
distance = self.distance_state(state)
|
||||
try:
|
||||
paths = first_order_image_sources(distance.direction_adm, distance.physical_distance_m,
|
||||
48000, self.config)
|
||||
except ValueError as error:
|
||||
raise ValueError("--sofa-room预设房间无法表示当前声源位置;关闭该开关可保留直接声") from error
|
||||
self.maximum_early_delay_samples = max(
|
||||
self.maximum_early_delay_samples, max(p.extra_delay_samples for p in paths))
|
||||
return paths
|
||||
|
||||
def direct_gain(self, state):
|
||||
return ReferenceDistanceProfileV1.direct_level_gain(self.distance_state(state))
|
||||
|
||||
def early_gain(self, path, measurement_radius_m):
|
||||
return (ReferenceDistanceProfileV1.PUBLIC_ROOM_CALIBRATION_GAIN * path.reflection_gain
|
||||
* measurement_radius_m / path.path_distance_m)
|
||||
|
||||
def set_source(self, source, state, gain, *, first=False, special_lfe=False):
|
||||
value = 0. if special_lfe else (float(gain) * ReferenceDistanceProfileV1.PUBLIC_ROOM_CALIBRATION_GAIN
|
||||
* ReferenceDistanceProfileV1.late_send(self.distance_state(state)))
|
||||
self.target[source] = value
|
||||
if first:
|
||||
self.current[source] = value
|
||||
|
||||
def filter_budget(self, field):
|
||||
needed = field.fft_size + int(math.ceil(self.early_delay_bound_samples)) + 64
|
||||
return 1 << (needed - 1).bit_length()
|
||||
|
||||
@property
|
||||
def early_delay_bound_samples(self):
|
||||
dimensions = np.asarray(self.config.dimensions_m)
|
||||
listener = np.asarray(self.config.listener_position_m)
|
||||
return 2 * float(np.max(np.maximum(listener, dimensions - listener))) * 48000 / self.config.speed_of_sound_m_s
|
||||
|
||||
def full_hrir(self, field, state):
|
||||
length = self.filter_budget(field)
|
||||
omega = 2 * math.pi * fft.rfftfreq(length)
|
||||
direct = np.roll(np.fft.irfft(field.spectrum(state.direction), field.fft_size),
|
||||
field.common_latency_samples, axis=-1)
|
||||
spectrum = fft.rfft(direct, length) * self.direct_gain(state)
|
||||
for path in self.paths(state):
|
||||
q = path.direction_adm[[1, 0, 2]] * [1, -1, 1]
|
||||
hrir = np.roll(np.fft.irfft(field.spectrum(q), field.fft_size),
|
||||
field.common_latency_samples, axis=-1)
|
||||
spectrum += (fft.rfft(hrir, length) * np.exp(-1j * omega * path.extra_delay_samples)
|
||||
* self.early_gain(path, field.measurement_radius_m))
|
||||
return fft.irfft(spectrum, length, axis=-1)
|
||||
|
||||
def process(self, source_block, direct_block):
|
||||
amount = np.arange(1, 129, dtype=np.float64)[:, None] / 128
|
||||
sends = self.current + (self.target - self.current) * amount
|
||||
self.pending_mono.append(np.einsum("ts,ts->t", source_block, sends))
|
||||
self.pending_direct.append(direct_block)
|
||||
self.current[:] = self.target
|
||||
if len(self.pending_mono) * 128 < self.batch_samples:
|
||||
return np.empty((0, 2))
|
||||
result = np.concatenate(self.pending_direct) + self.convolver.process_block(np.concatenate(self.pending_mono))
|
||||
self.pending_mono.clear()
|
||||
self.pending_direct.clear()
|
||||
return result
|
||||
|
||||
def info(self):
|
||||
return dict(enabled=True, schema=SCHEMA, preset=self.preset, asset=str(self.path.resolve()),
|
||||
late_fir=self.metadata, early_config=asdict(self.config),
|
||||
maximum_early_delay_samples=self.maximum_early_delay_samples,
|
||||
late_alignment_samples=self.alignment_samples,
|
||||
distance_coupling=ReferenceDistanceProfileV1.info(),
|
||||
high_precision_adaptation="full-HRIR early paths with fractional delay; PCM float64 late FIR",
|
||||
normalization="original project room coupling; not a measured BRIR")
|
||||
Reference in new issue
Block a user