% Acceptance-target ICASSP 2027 draft grounded only in archived measurements.
% Uses the repository's ICASSP 2027 author kit.
% Four technical pages plus an optional reference-only page.
\documentclass{article}
\usepackage{spconf}
\usepackage{amsmath,amssymb,graphicx,booktabs,multirow,hyperref,xcolor,float}
\hypersetup{hidelinks}
\newcommand{\vect}[1]{\boldsymbol{#1}}
\newcommand{\G}{\mathrm{G}}
\newcommand{\A}{\mathrm{A}}
\newcommand{\V}{\mathrm{V}}
\setlength{\emergencystretch}{2em}
\setcounter{topnumber}{5}
\setcounter{dbltopnumber}{5}
\renewcommand{\topfraction}{0.95}
\renewcommand{\dbltopfraction}{0.95}
\renewcommand{\textfraction}{0.05}
\renewcommand{\floatpagefraction}{0.75}
\renewcommand{\dblfloatpagefraction}{0.75}
\title{Egocentric Speech Anticipation with Omni Models:\\
Short-Window Evidence and Partial-Tail Refresh}
\name{\shortstack{Xin Wang, Dingtian Yan, Changdong Liu, Shengxiang Hu, \\
Xiaoju Dai, Li Zhang, Rong Zheng, and Guorun Chen}}
\address{China Telecom Corporation Limited Shanghai Branch}

\begin{document}
\ninept
\maketitle

\begin{abstract}
An egocentric conversational agent must anticipate when its unseen camera
wearer will speak from a causal multiparty audio--video stream.  Turn-taking
models and streaming Omni assistants address related problems, but the
cutoff-level availability of local evidence in an integrated Omni state is
underexplored for this wearer-centered task.  We examine two interfaces:
short-window encoder evidence (SWE) supplies recent audio and optional
person-crop vision directly to a frozen-Omni forecasting head; partial-tail
refresh (PTR) queries only the observed prefix of the current audiovisual
block at each 200-ms cutoff.  On EasyCom, the exploratory global-plus-audio
screen reaches 81.72\% mAP at 0.2~s and 65.11\% over ten horizons, versus
74.20/61.19\% for released EgoSpeak.  Pooled vision adds 0.29 mean-mAP
points, while an analysis-only visible-activity audit exposes further local
information.  A separate chunk screen suggests sensitivity to state
freshness but does not isolate PTR.  We specify an Ego4D transfer protocol;
its scores remain pending.  The evidence supports causal activity
anticipation, not semantic floor control or established cross-dataset gains.
\end{abstract}

\begin{keywords}
egocentric speech anticipation, multimodal foundation models, causal
streaming, voice activity projection, conversational agents
\end{keywords}

\section{Introduction}
\label{sec:intro}

An egocentric conversational agent could answer situated questions, supply
context, and assist its wearer during face-to-face conversation. To
participate naturally, it must decide not only \emph{what} to say but when to
begin, wait, or stop speaking. This requires interpreting mixed audio,
visible people's behavior, and linguistic content as the number and roles of
interlocutors change. A pause is not necessarily an invitation: two people
visible to the wearer may be talking to each other, and their turn exchange
should not trigger the agent's response. Since the wearer is normally
off-camera, the relevant target is not simply which visible face speaks now,
but whether the wearer is about to speak or cease speaking.
Both boundaries matter: the agent should withhold an entry during a
third-party exchange and yield when another participant takes the floor.
From a moving first-person view, face visibility and overlapping voices can
change independently; neither a silence threshold nor one detected face
provides a fixed map of who is interacting with the wearer. These timing
errors arise before response content is considered.

Prior work addresses complementary parts of this decision. Voice activity
detection (VAD) detects speech presence \cite{sohn1999vad}; dyadic voice
activity projection (VAP) predicts future speaker activity
\cite{ekstedt2022vap}, while Easy Turn and FastTurn combine acoustic and
linguistic evidence for spoken-agent turn detection
\cite{li2026easyturn,wang2026fastturn}. Audiovisual turn and backchannel
prediction exploits visible cues but is commonly evaluated with two
interlocutors \cite{russell2025mmvap,lin2025backchannel,
oconnorrussell2025noise}. Triadic VAP extends audio forecasting to fixed
three-person conversations
\cite{elmers2025triadic}; online three-party EOT has also used controlled
multimodal sensor data \cite{lee2024eot}. MuVAP handles a variable number of
speakers using single-camera video and face tracks, but studies visible
speakers from a
static third-party view \cite{qi2026muvap}. Device-directed speech detection
can combine acoustics, ASR output, and text to ask whether an utterance
addresses an assistant, yet the cited model does not observe visual
relations among interlocutors \cite{wagner2024ddsd}. EgoSpeak directly
forecasts the unseen wearer's future speech from causal
first-person audio--video on EasyCom and Ego4D \cite{kim2025egospeak,
donley2021easycom,grauman2022ego4d}. Multi-view next-speaker prediction,
first-person speaking/listening graphs, and addressee detection provide
related but distinct targets \cite{serj2024threem,jia2024avconv,
kong2024sicnet}. Egocentric active-speaker localization likewise concerns
current speaker evidence \cite{jiang2022asl,huh2025egoasd,clarke2025asd}.
Together, these studies leave open how an integrated streaming model should
retain cutoff-local evidence for forecasting the unseen wearer's activity in
a natural multiparty, first-person stream. This is a representation-and-timing
question, not a claim to first egocentric turn prediction. Our activity
labels do not establish addressee or semantic floor ownership.

Omni models couple modality encoders to a shared language-model state, so
audio, video, and text can inform streaming interaction and longer-range
semantic context \cite{xu2025qwenomni,tian2026roma,chen2024videollmonline}.
Qwen2.5-Omni has released 3B and 7B variants. Its block-wise encoders and
time-aligned audio--video interleaving feed a Thinker for integrated
understanding; a separate Talker generates speech \cite{xu2025qwenomni}.
We use frozen 3B Thinker readouts; 7B is a planned transfer control, not a
measured result. The native audio attention block spans 2~s, whereas our
wearer forecast updates every 200~ms. Holding only completed blocks leaves
stale context between boundaries; forcing 200-ms commits changes the native
block construction and may alter its representation. Neither implies that
all Omni models lack local evidence. An integrated, multi-layer state can
carry broader audiovisual and linguistic context, yet transient cues may be
less accessible to a small head than encoder-side features themselves
\cite{lin2023lavish,rouditchenko2024whisperflamingo}.

We therefore retain the global Thinker state while exposing recent modality
evidence at each causal cutoff (Fig.~\ref{fig:overview}). EasyCom screens
suggest that global context and local audio are complementary; gains from
pooled vision and isolated PTR effects remain unproven. This study makes
three contributions: (1) short-window encoder evidence (SWE) supplies recent
audio and optional person-crop vision to a frozen-Omni forecasting head;
(2) partial-tail refresh (PTR) queries the observed current-block prefix
without committing it to persistent history; and (3) detailed EasyCom
analyses accompany a specified Ego4D transfer protocol. Matched PTR,
Ego4D scores, and event behavior remain pending.

\begin{figure}[t]
\centering
\includegraphics[width=\columnwidth]{figures/system_overview_onecolumn.pdf}
\caption{Method overview at cutoff $t_n$. Top: SWE joins frozen Omni context
with recent audio and optional pooled person-crop evidence in the forecasting
head. Bottom: PTR reuses completed 2-s blocks and temporarily queries only
the observed current-block tail at each 200-ms cutoff. The tail is not
committed to persistent history.}
\label{fig:overview}
\end{figure}

\section{Method}
\label{sec:method}

\subsection{Task and Short-Window Encoder Evidence}

At the 5-Hz cutoff $t_n=0.2n$~s, the model observes only media available by
$t_n$ and predicts activity at $t_n+h$, where
$h\in\{0.2,0.4,\ldots,2.0\}$~s.  Each
horizon has three channels in fixed order: background, camera wearer, and
aggregate others.  Wearer and others may overlap; no output identifies an
individual speaker, addressee, or semantic end of turn.

The global feature $\vect g_n$ concatenates the final four frozen
Qwen2.5-Omni-3B Thinker readouts and projects them to 2048 dimensions.  It
already contains audio and video context; $\G$ is not audio-free.  SWE
provides a separate short-window path so the head need not recover all
cutoff-local detail from the integrated state. Local audio $\vect a_n$ crops
the latest one-second mixed
waveform \emph{before} preprocessing, runs the frozen Qwen audio encoder, and
averages valid tokens.  Optional $\vect v_n$ averages frozen vision tokens
inside provided person boxes, then across people and valid causal 2-FPS
frames in the latest second. This pooling has no identity or mouth-motion trajectory;
provided boxes do not imply an online detector.

Each enabled local feature is layer-normalized, projected to 256 dimensions,
and paired with a validity bit.  The trainable head is
\begin{equation}
 \widehat{\vect Y}_{n}=
 \operatorname{softmax}_{c}F_{\theta}
 \bigl[\vect g_n;\widetilde{\vect a}_n;m_n^a;
       \widetilde{\vect v}_n;m_n^v\bigr],
 \label{eq:fusion}
\end{equation}
where omitted modalities remove their terms and $F_\theta$ is a
layer-normalized MLP with a 30-logit output.  We train only the projections and
head with the EgoSpeak multi-positive cross-entropy over causal-valid
source--horizon pairs.  The Omni and modality encoders remain frozen, so this
is frozen-backbone adaptation rather than end-to-end training.

\subsection{Causal Partial-Tail Refresh}

PTR uses source-aligned 2-s blocks under an 8-s maximum presentation cap
(Fig.~\ref{fig:overview}). After warm-up, three completed blocks and the
observed current tail are available; span varies with block phase. Reusing
completed modality payloads, we crop the tail at $t_n$ and query it in a
temporary cache. The tail and query are not committed. Only completed
blocks enter persistent history; session and source discontinuities reset
caches. Thus each 5-Hz readout sees the observed prefix without future
backfill. To test whether access policy matters, the matched design crosses
completed-only versus PTR readouts with $\A$ on/off at an identical 8-s cap;
the separate 2--12-s cap sweep tests context length. Those comparisons are
pending, so PTR is a causal access rule rather than a demonstrated gain.

\subsection{Visible-Activity Information Audit}

To distinguish missing information from ineffective learned vision, we build
analysis-only features from transcript-derived \emph{past} activity.  At each
cutoff, visible non-wearer participants receive two seconds of binary history
sampled on the same 5-Hz grid.  The preparation fails if its aggregate
activity disagrees with the released target.  We compare: (i) visibility with
activity zeroed, (ii) per-person histories, (iii) identities shuffled while
preserving active-person counts at every lag, (iv) histories delayed by one
second, and (v) one OR-pooled aggregate-visible history.  These conditions
never expose future activity, but their speech labels make them privileged
diagnostics, not deployable features or upper bounds.

\input{tables_compact}
% Historical full-precision table layouts retained as source audit only.
\iffalse
\begin{table*}[t]
\caption{Measured EasyCom screens (\%). Panel A: deployable models; Panel B:
three-seed privileged past-activity audit, which is not deployable. Mean is
ten-horizon dense mAP; On/Off are raw wearer endpoint AP, not semantic events.
F3 is a no-box, two-frame causal full-frame screen; it and the historical
deployable rows are exploratory seed-0 runs with unmatched head/training
details. F1 has three seeds. Dashes are unavailable, not zero.}
\label{tab:main}
\centering
\normalsize
\renewcommand{\arraystretch}{0.87}
\setlength{\tabcolsep}{5.0pt}
\begin{tabular}{@{}lccccc@{}}
\toprule
Method & $\mathrm{mAP}_{.2}\uparrow$ & $\mathrm{WAP}_{.2}\uparrow$
& Mean$\uparrow$ & On$\uparrow$ & Off$\uparrow$ \\\\
\midrule
EgoSpeak MiniROADA A+V & 74.204 & 63.750 & 61.193 & 24.491 & 38.024 \\\\
Recent Qwen audio $\A$ & 79.692 & 84.100 & 60.508 & -- & -- \\\\
Omni global $\G$ & 73.446 & 77.867 & 60.849 & -- & -- \\\\
Omni $\G+\A$ & 81.723 & 85.066 & 65.109 & 25.960 & 45.251 \\\\
Omni $\G+\A+$pooled-$\V$ & 82.027 & 85.086
& 65.400 & 26.019 & 45.371 \\\\
No-box full-frame F3 & 82.380 & -- & 65.540 & -- & -- \\\\
Current-frame person set F1 & $81.777{\pm}0.156$ & --
& $64.951{\pm}0.095$ & -- & -- \\\\
Matched-width $\G$ (L2) & -- & -- & -- & -- & -- \\\\
Past-delayed $\A$ (L3) & -- & -- & -- & -- & -- \\\\
Current-state persistence (L4) & -- & -- & -- & -- & -- \\\\
\bottomrule
\end{tabular}
\par\smallskip
\emph{Panel B: privileged past-activity audit (mean $\pm$ sample SD).}\par\smallskip
\normalsize
\setlength{\tabcolsep}{3.2pt}
\begin{tabular}{@{}lccc@{}}
\toprule
Extra condition & $\mathrm{mAP}_{.2}$ & $\mathrm{WAP}_{.2}$ & Mean \\\\
\midrule
None (audio baseline) & $81.869{\pm}.049$ & $85.264{\pm}.110$ & $65.177{\pm}.058$ \\\\
Visibility only & $81.945{\pm}.098$ & $85.200{\pm}.144$ & $65.217{\pm}.048$ \\\\
Activity delayed 1 s & $81.951{\pm}.086$ & $85.270{\pm}.137$ & $65.341{\pm}.051$ \\\\
Shuffled person IDs & $85.917{\pm}.085$ & $85.577{\pm}.246$ & $66.460{\pm}.090$ \\\\
Per-person activity & $86.266{\pm}.182$ & $85.608{\pm}.220$ & $66.660{\pm}.135$ \\\\
Aggregate visible activity & $\mathbf{86.696{\pm}.085}$ & $\mathbf{85.836{\pm}.147}$
& $\mathbf{66.951{\pm}.022}$ \\\\
\bottomrule
\end{tabular}
\end{table*}

\begin{table*}[t]
\caption{Chunk and context audit. Panel A is an unmeasured matched T/C
matrix: each row pairs $\G$ and $\G+\A$ on common valid cutoffs. Panel B is
a separate exploratory seed-0 global-only screen (10 epochs, 8-s cap,
2-FPS video); its rows are not entries in Panel A. Dashes are pending.}
\label{tab:stream_context}
\centering\normalsize
\renewcommand{\arraystretch}{0.87}
\setlength{\tabcolsep}{4pt}
\begin{tabular}{@{}llccccc@{}}
\toprule
Group & Refresh / cap & $\G$ mAP & $\G+\A$ mAP & $\Delta$ mAP
& $\Delta$ On & $\Delta$ Off \\
\midrule
T & Completed-only, 8 s & -- & -- & -- & -- & -- \\
T & Observed-tail, 8 s & -- & -- & -- & -- & -- \\
\midrule
C & Tail-aware, 2 s & -- & -- & -- & -- & -- \\
C & Tail-aware, 4 s & -- & -- & -- & -- & -- \\
C & Tail-aware, 6 s & -- & -- & -- & -- & -- \\
C & Tail-aware, 8 s & -- & -- & -- & -- & -- \\
C & Tail-aware, 10 s & -- & -- & -- & -- & -- \\
C & Tail-aware, 12 s & -- & -- & -- & -- & -- \\
\bottomrule
\end{tabular}
\par\smallskip
\emph{Panel B: reported 200-ms chunk screen; dense mAP (\%).}\par\smallskip
\begin{tabular}{@{}lccc@{}}
\toprule
Global feature construction & 0.2-s mAP & Mean mAP & Processor calls \\
\midrule
Native 2-s completed hold & 59.62 & 55.19 & 9,539 \\
Non-native 200-ms commits & 67.05 & 57.84 & 95,453 \\
Completed blocks + observed tail & 70.85 & 59.17 & -- \\
\bottomrule
\end{tabular}
\end{table*}

\fi
\begin{table}[t]
\caption{Pending paired $\G\rightarrow\G+\A$ transfer (unmeasured).
EC is EasyCom; MiniCPM first needs readout/refresh/history audits.}
\label{tab:backbone}
\centering\normalsize
\setlength{\tabcolsep}{3pt}
\begin{tabular}{@{}lccc@{}}
\toprule
Backbone & $\G$ & $\G+\A$ & $\Delta$ \\
\midrule
EC: Omni 3B & -- & -- & -- \\
EC: Omni 7B & -- & -- & -- \\
EC: MiniCPM-o 4.5 & -- & -- & -- \\
Ego4D: Omni 3B & -- & -- & -- \\
\bottomrule
\end{tabular}
\end{table}

\begin{table}[t]
\caption{H result slots: predeclared activity slices (unmeasured). Report
positive/negative counts and per-session scores; AP is undefined for a
pure-negative slice, which instead uses calibrated FPR.}
\label{tab:hard_slices}
\centering\normalsize
\setlength{\tabcolsep}{2.5pt}
\begin{tabular}{@{}lccc@{}}
\toprule
Slice & $N_+/N_-$ & AP & FPR \\
\midrule
Wearer onset & -- & -- & -- \\
Wearer offset & -- & -- & -- \\
Other pause (negative) & -- & n/a & -- \\
Overlap (negative) & -- & n/a & -- \\
\bottomrule
\end{tabular}
\end{table}

\begin{table}[t]
\caption{S result slots: full-path cost on the same hardware (unmeasured).
Include I/O and block transitions; logical 5 Hz is not measured throughput.}
\label{tab:efficiency}
\centering\normalsize
\setlength{\tabcolsep}{3pt}
\begin{tabular}{@{}lccc@{}}
\toprule
Stage & P50 ms & P95 ms & Peak GB \\
\midrule
Completed block & -- & -- & -- \\
Observed tail & -- & -- & -- \\
Local path + head & -- & -- & -- \\
Full path & -- & -- & -- \\
\bottomrule
\end{tabular}
\end{table}

\section{Experiments}
\label{sec:experiments}

\textbf{Data and protocol.}
We use EasyCom with the EgoSpeak official split: Sessions~4--12 for training
and Sessions~1--3 for testing.  Inputs and targets share a 5-Hz grid.  Heads
are trained for four fixed epochs on all training sessions without test-time
checkpoint selection.  The deployable feature matrix is an archived
single-seed screen; the information audit uses seeds 0, 1, and 2 with an
identical fixed recipe.  We therefore report standard deviations only for the
latter and treat small differences in the former descriptively.

\textbf{Ego4D transfer protocol (pending results).}
Ego4D audiovisual clips \cite{grauman2022ego4d} use the existing EgoSpeak
manifest and targets, with 346 training and 87 test clips.  The same 5-Hz
cutoffs and local 1-s encoder windows define $\G$, $\G+\A$, $\G+\V$, and
$\G+\A+\V$ comparisons; visual validity is retained rather than silently
dropping no-box rows.  The repository contains the extraction and training
workflow but no archived Ego4D score or matched PTR control.  Hence this
protocol is specified, not reported as an observed cross-dataset gain.

\textbf{Metrics.}
At each horizon we compute AP for the three activity channels over common
causal-valid rows, then average classes to obtain mAP and average all ten
horizons to obtain mean mAP.  We also report wearer AP at 0.2~s.  For endpoint
diagnostics, onset AP conditions source rows on the wearer being silent and
scores future speech with $p(\mathrm{wearer})$; offset AP conditions on wearer
speech and scores future silence with $1-p(\mathrm{wearer})$.  These
threshold-free quantities average ten horizons.  They are not one-event-one-
vote detection, semantic ENTRY/YIELD, or evidence of addressee understanding.

\textbf{Comparisons.}
We evaluate released EgoSpeak MiniROADA A+V; recent audio $\A$; global Omni
$\G$; $\G+\A$; and $\G+\A+$pooled-$\V$.  A three-seed current-frame
frame-set attention screen tests whether a richer person aggregation is
already sufficient.  Because that screen used Session~12 model selection
whereas the historical pooled row did not, their difference is diagnostic,
not a matched causal attribution.

\textbf{Pre-specified analyses.}
We freeze six control families: (L) capacity and recency, (T) tail
refresh crossed with local audio, (C) six context caps, (B) paired backbone
transfer, (H/Q) error slices and timelines, and (S) full-path efficiency.
They share the official split and physical cutoffs; the 8-s T/C row reuses
one run.  The source retains unmeasured hypotheses and falsifiers.

\section{Results and Analysis}
\label{sec:results}

\subsection{EasyCom: Local Encoder Evidence}

Table~\ref{tab:main} shows that recent encoder-side audio $\A$ is strong at
0.2~s while integrated $\G$ is slightly stronger on the ten-horizon mean.
Their seed-0 fusion gains 4.60 mean-mAP points over $\A$ and 4.26 over
$\G$.  Relative to released EgoSpeak, $\G+\A$ gains 7.52 points at
0.2~s and 3.92 mean-mAP points.  Raw wearer offset AP rises by 7.23
points, onset AP by only 1.47: dense gains do not imply equal improvement
at both activity boundaries.

The $\G$-only head has more trainable parameters and longer history than the
$\A$-only head. Thus this screen is consistent with predictive
complementarity, not a capacity-matched proof that the Thinker lacks a
specific local cue. Individual $\A$ and $\G$ horizon curves are unavailable
under the same causal-valid summary and are not reconstructed in Table~\ref{tab:main}.

% Retained as a planning aid; illustrative, unmeasured patterns do not belong
% in the page-limited submission preview.
\iffalse
\begin{table*}[t]
\caption{Six-group \textbf{illustrative scenario, not measured results}.
These are conditional, pre-run interpretations for the pending matrix, not
EasyCom scores.  $\Delta$ denotes paired mean-mAP change on common valid
cutoffs; signs and shape must be replaced by measured values even if contrary
to the story.  L/T/C/B require seeds 0--2 and per-session reporting.}
\label{tab:scenario}
\centering
\normalsize
\renewcommand{\arraystretch}{1.12}
\setlength{\tabcolsep}{4.2pt}
\begin{tabular}{@{}p{0.095\textwidth}p{0.29\textwidth}p{0.29\textwidth}p{0.235\textwidth}@{}}
\toprule
Group & Frozen comparison & Illustrative pattern \emph{if observed} & Falsifier / interpretation limit \\
\midrule
L1--4 & $\A,\G,\G+\A,\G+\A+\V$; matched-width $\G$;
past-delayed local cues; current-state persistence
& $\Delta(\G+\A-\G)>0$ after width matching; delayed $\A$ loses
near-horizon benefit; persistence does not recover the gain
& Width-only or persistence matches fusion, or delay does not hurt:
do not attribute gain to timely distinct evidence. \\
\addlinespace[2.5pt]
T1--2 & 2-s completed-only vs 200-ms observed-tail refresh,
crossed with $\A$ on/off; causal replay and phase audit
& Tail helps most without $\A$; local $\A$ still adds at each refresh;
future-only media never changes prior readouts
& No independent local gain under tail refresh implies redundancy;
replay/leakage failure invalidates timing claims. \\
\addlinespace[2.5pt]
C1--2 & Genuine 2/4/6/8/10/12-s feature extraction; fixed 1-s $\A$;
add $\G$-only at each cap for a window-stability claim
& Fused performance plateaus around mid-range caps while
$\G$-only remains more cap-sensitive
& If long history substitutes for $\A$, local-evidence claim narrows;
without C2, no robustness comparison is justified. \\
\addlinespace[2.5pt]
B0--2 & Paired $\G$ and $\G+\A$ on Qwen 3B/7B and, after causal
interface audit, MiniCPM-o 4.5
& Positive within-backbone paired $\Delta$ on all admissible rows;
absolute backbone ranking is not inferred
& Failed causal/history match is unsupported, not zero gain;
one negative paired row defeats universal transfer. \\
\addlinespace[2.5pt]
H1/Q1 & Predefined onset/offset and other-pause/overlap slices;
same-horizon, cutoff-marked case selection
& Offset gains coexist with hard wearer-onset negatives; examples
explain, rather than replace, counted slice statistics
& Pure-negative slice AP is undefined; selected examples cannot
establish reduced false-entry rate. \\
\addlinespace[2.5pt]
S1 & End-to-end p50/p95 latency and peak memory, including I/O,
encoding, tail recomputation, local path, and boundaries
& A feasible throughput--quality tradeoff can be plotted
against 200-ms output cadence
& If p95 exceeds cadence, describe logical 5-Hz prediction only,
not real-time deployment. \\
\bottomrule
\end{tabular}
\end{table*}
\fi

\subsection{EasyCom: Visual Evidence and Ablations}

Adding pooled $\V$ to $\G+\A$ produces only +0.304 points at 0.2~s and
+0.291 mean mAP.  Its wearer increment is +0.020 at 0.2~s and +0.061 when
averaged over horizons; onset/offset changes are +0.059/+0.120.  A richer
current-frame person-set model is stable across seeds but reaches lower mean
mAP than the historical pooled row under a non-matched selection protocol.
These results do not support a claim of learned speaker grounding. A separate
seed-0 no-box full-frame F3 screen reaches 82.38\% at 0.2~s and 65.54\%
mean mAP, versus 81.72/65.11\% for the existing $\G+\A$ row under the same
causal-valid dense protocol. F3 adds a two-frame 2-FPS token history and a
shared GRU, while head capacity and training batch differ; raw boundary
metrics and repeat seeds are unavailable. Thus the +0.66/+0.43-point
difference does not isolate visual motion or floor behavior.

Table~\ref{tab:oracle} locates the missing information. Aggregate visible
activity improves over the audio baseline by 4.826 points at 0.2~s and 1.775
mean-mAP points.  Visibility alone changes mean mAP by only +0.040, and
one-second-delayed activity by +0.164.  Thus availability or extra parameters
cannot explain the oracle gain.  Per-person activity exceeds shuffled identity
by only 0.200 mean-mAP points and is itself 0.291 below the aggregate
condition.  The current target therefore supports timely visible-floor
activity as useful information, but not the necessity of identity continuity.
The majority of the oracle's 0.2-s macro gain comes from background and
others; wearer AP rises by only 0.572.  This is why neither the oracle nor a
dense mAP gain establishes fewer false wearer entries.

\begin{figure}[t]
\centering
\fbox{\begin{minipage}[c][18mm][c]{0.94\columnwidth}
\centering
\textbf{Q1 case slots: examples pending}\\[2pt]
Onset / other-pause hard negative \quad|\quad Offset / overlap\\
Show source cutoff, observed activity and same-horizon wearer scores.
\end{minipage}}
\caption{Reserved H/Q case figure. Select examples by a frozen rule after
the slice counts in Table~\ref{tab:hard_slices} are available. No case or
behavioral improvement is asserted by this placeholder.}
\label{fig:hq_cases}
\end{figure}

\subsection{Chunk Timing and Cross-Dataset Limits}

Table~\ref{tab:chunk} reports a separate global-only
chunk-construction screen.  Non-native 200-ms commits exceed native 2-s hold
at 0.2~s (67.05 versus 59.62\% mAP), but use 95,453 rather than 9,539
processor calls over 12 sessions.  Completed blocks plus observed tail reach
70.85\%; that older bank is not extraction-matched.  Freshness and chunk
construction vary together, so this is motivation for, not evidence of, an
isolated PTR benefit or real-time throughput. Table~\ref{tab:stream_context}
reserves the matched tail $\times$ audio and context-cap tests.
Tables~\ref{tab:backbone}--
\ref{tab:efficiency} reserve backbone, hard-slice, and cost analyses; the
cutoff-marked H/Q case in Fig.~\ref{fig:hq_cases} remains unmeasured.
\textbf{Historical LoRA diagnostic.}
A single-run EasyCom 8-s/2-FPS screen used sparse training anchors (1~Hz,
plus 5~Hz near transitions) and dense 5-Hz evaluation.  Within that legacy
pipeline, strict mean mAP was 58.17\% for a frozen dense-cache control,
57.21\% for frozen sparse training, and 56.21\% for a separate three-epoch
Thinker-LoRA run initialized from a trained frozen head.  An epoch-1 LoRA
weights-only continuation fell to 54.21\% after optimizer/scheduler reset.
Sparse frozen training is 0.96 points below the dense control; the separate
LoRA run is another 1.01 below sparse frozen, but the epoch budgets differ.
Sparse-train/dense-test mismatch and the optimizer reset are possible, not
isolated, explanations.
Missing remote raw metrics, matched seeds, and feature equivalence make this
a negative recipe diagnostic, not a Table~\ref{tab:main} $\G+\A$ comparison
or proof that LoRA is inherently harmful.
Ego4D has no archived test metrics in this checkout, so transfer cannot yet
be claimed.  The oracle uses privileged labels, provided boxes omit online
detection, and aggregate others cannot establish addressee or semantic floor
ownership.

\subsection{Decision Rules and Reproducibility}

Matched comparisons require identical cutoffs and targets; archive source
timestamps, valid-pair counts, seeds, per-session AP, trainable counts, and
checkpoint/processor revisions.  The fixed recipe and selection rules use
training-side evidence only.  Already inspected test sessions make repeat
seeds exploratory.  Raw endpoint AP is not one-event-one-vote ENTRY/YIELD:
response windows must end at the next other onset, and yield windows at the
next other offset.  Behavioral claims await a real-timeline evaluator audit.

\section{Conclusion}

For egocentric when-to-speak forecasting, cutoff-aligned access to recent
encoder evidence is a useful complement to frozen Omni context on EasyCom;
the strongest measured boundary difference is at wearer speech offset.
Pooled vision recovers little of the timely visible-activity information
revealed by the privileged audit. PTR supplies a causal 5-Hz readout rule,
but its independent predictive and efficiency effects still require matched
tests. Ego4D transfer and censored event evaluation remain necessary before
claiming generalizable or improved semantic floor behavior.

\section{Acknowledgment}
OpenAI Codex assisted with drafting and figure layout; the authors remain
responsible for all experimental claims and final content.

\clearpage
\bibliographystyle{IEEEbib}
\bibliography{references}
\end{document}