W12 follow-up: consume in-band FEC, drop redundant DTX

Fixes the two P2 efficacy findings from the Codex audit of the W12
profiles feature.

FEC was enabled on the encoder but never used: the jitter buffer's
loss path did pure PLC, so the redundancy was wasted bitrate. Now the
gap path reconstructs the lost frame from the next buffered packet via
Opus in-band FEC (new `AudioDecoder::decode_fec`, libopus decode with
fec=true into a one-frame buffer), keeping that packet for its own
normal decode and falling back to PLC if FEC decode fails. This is the
documented libopus FEC pattern; receiver-side only, no wire change.

DTX was enabled on BadNetwork but provided no benefit — the capture
noise gate already suppresses silence transmission, and the broadcast
DTX silence packets only created seq gaps that grew the jitter cushion.
All profiles now set dtx=false (plumbing kept for a future revisit).

Adds a jitter-buffer test proving FEC reconstruction beats pure PLC
(RMS error < 0.75x) and that the FEC source packet stays buffered.
500 lib tests, clippy + fmt clean, release build clean.

Co-Authored-By: Codex (gpt-5.5) <noreply@openai.com>
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
2026-06-30 16:56:19 -04:00
co-authored by Codex Claude Opus 4.8
parent d92d0f6f6b
commit 5f52aa1506
5 changed files with 116 additions and 12 deletions
+1 -1
View File
@@ -3139,7 +3139,7 @@ fn audio_profile_hint(profile: AudioProfile) -> &'static str {
} }
AudioProfile::Balanced => "Default: voice quality with light loss recovery.", AudioProfile::Balanced => "Default: voice quality with light loss recovery.",
AudioProfile::BadNetwork => { AudioProfile::BadNetwork => {
"Most resilient on a lossy/congested link: extra loss recovery, lower bitrate." "Most resilient on a lossy/congested link: heavier loss recovery, lower bitrate."
} }
} }
} }
+3
View File
@@ -20,6 +20,9 @@ pub trait AudioDecoder: Send {
/// If `compressed` is `None` (or `Some(&[])`), it indicates packet loss, /// If `compressed` is `None` (or `Some(&[])`), it indicates packet loss,
/// enabling the decoder to perform packet loss concealment (PLC). /// enabling the decoder to perform packet loss concealment (PLC).
fn decode(&mut self, compressed: Option<&[u8]>) -> Result<Vec<i16>, CodecError>; fn decode(&mut self, compressed: Option<&[u8]>) -> Result<Vec<i16>, CodecError>;
/// Reconstructs the previous lost frame from the next packet's in-band FEC.
fn decode_fec(&mut self, next_payload: &[u8]) -> Result<Vec<i16>, CodecError>;
} }
pub mod opus_impl; pub mod opus_impl;
+16 -5
View File
@@ -40,7 +40,7 @@ pub fn opus_params(profile: AudioProfile) -> OpusParams {
bitrate: 20_000, bitrate: 20_000,
inband_fec: true, inband_fec: true,
packet_loss_perc: 25, packet_loss_perc: 25,
dtx: true, dtx: false,
}, },
} }
} }
@@ -162,6 +162,19 @@ impl AudioDecoder for OpusDecoder {
pcm.truncate(decoded_per_channel * channels_count); pcm.truncate(decoded_per_channel * channels_count);
Ok(pcm) Ok(pcm)
} }
fn decode_fec(&mut self, next_payload: &[u8]) -> Result<Vec<i16>, CodecError> {
let channels_count = self.channels_count();
let mut pcm = vec![0i16; self.frame_samples * channels_count];
let decoded_per_channel = self
.decoder
.decode(next_payload, &mut pcm, true)
.map_err(|e| CodecError::Decode(format!("Opus FEC decoding failed: {}", e)))?;
pcm.truncate(decoded_per_channel * channels_count);
Ok(pcm)
}
} }
#[cfg(test)] #[cfg(test)]
@@ -180,10 +193,8 @@ mod tests {
assert!(bal.inband_fec); assert!(bal.inband_fec);
assert!(bad.inband_fec); assert!(bad.inband_fec);
// BadNetwork is the only profile that enables DTX, and it expects the // Capture-side gating suppresses silence; no profile adds Opus DTX.
// heaviest loss. assert!(!low.dtx && !bal.dtx && !bad.dtx);
assert!(bad.dtx);
assert!(!low.dtx && !bal.dtx);
assert!(bad.packet_loss_perc > bal.packet_loss_perc); assert!(bad.packet_loss_perc > bal.packet_loss_perc);
// BadNetwork trims base bitrate to make room for FEC redundancy. // BadNetwork trims base bitrate to make room for FEC redundancy.
+1 -1
View File
@@ -105,7 +105,7 @@ pub enum AudioProfile {
#[default] #[default]
Balanced, Balanced,
/// Maximum resilience on a lossy/congested link: in-band FEC tuned for heavy /// Maximum resilience on a lossy/congested link: in-band FEC tuned for heavy
/// loss plus DTX, at a lower bitrate to leave headroom for the redundancy. /// loss, at a lower bitrate to leave headroom for the redundancy.
BadNetwork, BadNetwork,
} }
+95 -5
View File
@@ -202,11 +202,15 @@ impl JitterBuffer {
None None
} else { } else {
// Gap with later packets already buffered: a packet was lost // Gap with later packets already buffered: a packet was lost
// or reordered out of window. Conceal this frame via Opus PLC // or reordered out of window. First try Opus in-band FEC from
// and grow the cushion — the jitter beat our current delay. // the next packet; if unavailable, fall back to plain PLC.
self.next_seq = Some(next.wrapping_add(1)); self.next_seq = Some(next.wrapping_add(1));
self.note_disruption(); self.note_disruption();
self.decoder.decode(None).ok() let next_payload = self.packets.values().next().expect("non-empty");
self.decoder
.decode_fec(next_payload)
.or_else(|_| self.decoder.decode(None))
.ok()
} }
} }
} }
@@ -221,8 +225,8 @@ impl JitterBuffer {
#[cfg(test)] #[cfg(test)]
mod tests { mod tests {
use super::*; use super::*;
use crate::codec::AudioEncoder; use crate::codec::opus_impl::{OpusDecoder, OpusEncoder, OpusParams};
use crate::codec::opus_impl::OpusEncoder; use crate::codec::{AudioDecoder, AudioEncoder};
use opus::{Application, Channels}; use opus::{Application, Channels};
/// A real, decodable Opus packet for one 20ms mono frame at amplitude `amp`. /// A real, decodable Opus packet for one 20ms mono frame at amplitude `amp`.
@@ -233,6 +237,32 @@ mod tests {
enc.encode(&pcm).unwrap() enc.encode(&pcm).unwrap()
} }
fn tone_frame(enc: &mut OpusEncoder, amp: i16, frame_index: usize) -> Vec<u8> {
let pcm: Vec<i16> = (0..FRAME_SAMPLES)
.map(|i| {
let sample_index = frame_index * FRAME_SAMPLES + i;
let t = sample_index as f32 / 48_000.0;
let fundamental = (t * 220.0 * 2.0 * std::f32::consts::PI).sin();
let harmonic = (t * 440.0 * 2.0 * std::f32::consts::PI).sin();
((fundamental * 0.7 + harmonic * 0.3) * amp as f32) as i16
})
.collect();
enc.encode(&pcm).unwrap()
}
fn rms_error(a: &[i16], b: &[i16]) -> f64 {
assert_eq!(a.len(), b.len());
let sum_sq: f64 = a
.iter()
.zip(b)
.map(|(&left, &right)| {
let diff = left as f64 - right as f64;
diff * diff
})
.sum();
(sum_sq / a.len() as f64).sqrt()
}
#[test] #[test]
fn buffers_then_plays_in_order() { fn buffers_then_plays_in_order() {
let mut enc = OpusEncoder::new(48000, Channels::Mono, Application::Voip).unwrap(); let mut enc = OpusEncoder::new(48000, Channels::Mono, Application::Voip).unwrap();
@@ -289,6 +319,66 @@ mod tests {
assert!(jb.pop_frame().is_none()); assert!(jb.pop_frame().is_none());
} }
#[test]
fn uses_in_band_fec_from_next_packet_for_gap() {
let mut enc = OpusEncoder::new(48000, Channels::Mono, Application::Voip).unwrap();
enc.apply_params(&OpusParams {
bitrate: 20_000,
inband_fec: true,
packet_loss_perc: 60,
dtx: false,
})
.unwrap();
let dropped_seq = 5usize;
let amps = [1800, 1800, 1800, 1800, 1800, 12_000, 12_000, 12_000];
let packets: Vec<Vec<u8>> = amps
.into_iter()
.enumerate()
.map(|(seq, amp)| tone_frame(&mut enc, amp, seq))
.collect();
let mut expected_decoder = OpusDecoder::new(48000, Channels::Mono, FRAME_SAMPLES).unwrap();
for packet in packets.iter().take(dropped_seq) {
expected_decoder.decode(Some(packet)).unwrap();
}
let expected_lost = expected_decoder
.decode(Some(&packets[dropped_seq]))
.unwrap();
let mut plc_decoder = OpusDecoder::new(48000, Channels::Mono, FRAME_SAMPLES).unwrap();
for packet in packets.iter().take(dropped_seq) {
plc_decoder.decode(Some(packet)).unwrap();
}
let pure_plc = plc_decoder.decode(None).unwrap();
let mut jb = JitterBuffer::new().unwrap();
for (seq, packet) in packets.iter().enumerate() {
if seq != dropped_seq {
jb.insert(seq as u32, packet.clone());
}
}
for _ in 0..dropped_seq {
assert_eq!(jb.pop_frame().map(|frame| frame.len()), Some(FRAME_SAMPLES));
}
let recovered = jb.pop_frame().expect("gap should be reconstructed");
assert_eq!(recovered.len(), FRAME_SAMPLES);
assert!(
jb.packets.contains_key(&(dropped_seq as u32 + 1)),
"FEC source packet must remain buffered for normal decode"
);
assert_eq!(jb.pop_frame().map(|frame| frame.len()), Some(FRAME_SAMPLES));
let fec_error = rms_error(&recovered, &expected_lost);
let plc_error = rms_error(&pure_plc, &expected_lost);
assert!(
fec_error < plc_error * 0.75,
"FEC reconstruction should be materially closer than PLC (fec_error={fec_error}, plc_error={plc_error})"
);
}
#[test] #[test]
fn drops_packets_already_played() { fn drops_packets_already_played() {
let mut enc = OpusEncoder::new(48000, Channels::Mono, Application::Voip).unwrap(); let mut enc = OpusEncoder::new(48000, Channels::Mono, Application::Voip).unwrap();