wx44wx/icassp2027-experiment
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'main' of http://182.92.86.220:8300/wx44wx/icassp2027-experiment

Browse Source 
# Conflicts:
#	docs/easycom_event_review_tool.md
#	manuscript/main/main.tex
#	prepare_easycom_eot_int_review.py
This commit is contained in:
Xin Wang
2026-09-14 23:50:51 +08:00
parent 2f9ccfad88 65347dd75d
commit 026d89978f
12 changed files with 329 additions and 109 deletions
Download Patch File Download Diff File Expand all files Collapse all files
manuscript/main/main.tex
+13 -11
View File
@@ -567,15 +567,15 @@ wearer episode. This grouping changes only the behavioral-event layer, not the
source intervals or dense targets.
\textbf{EOT-response.}
Starting from a floor-level wearer onset at $t_b$, we search backward for a
plausible non-wearer floor release at $t_r$. A candidate is retained only when
the interval from $t_r$ to $t_b$ contains neither intervening wearer speech nor
a competing non-wearer onset. The record stores both $t_r$ as the
\emph{opportunity anchor} and $t_b$ as the \emph{behavior anchor}, together with
the response delay $t_b-t_r$. Silence duration alone does not reject a
candidate. The LLM and human annotator then decide whether the release is
conversationally valid and whether the wearer speech is a genuine floor take.
Unpaired wearer onsets remain audit controls.
Starting from a floor-level wearer onset at $t_b$, we search backward for
plausible non-wearer floor releases. A release at $t_r$ is retained as an option
only when the interval from $t_r$ to $t_b$ contains neither intervening wearer
speech nor a competing non-wearer onset. Each wearer onset contributes at most
one review item: $t_b$ is its immutable \emph{behavior anchor}, and the item
stores every admissible \emph{opportunity-anchor} option and response delay.
Silence duration alone does not reject an option. A positive EOT annotation
must select one supplied release; neither the LLM nor the human can invent or
move a trigger timestamp. Unpaired wearer onsets remain audit controls.
\textbf{INT-yield.}
Starting from an episode-ending wearer offset $t_y$, we search backward inside
@@ -609,12 +609,14 @@ measurements, transcripts, and target-of-speech metadata when available. It is
instructed not to equate onset with entry, offset with yield, silence with EOT,
or overlap with interruption, and not to invent unavailable prosody, gaze, or
intent. EasyCom's \texttt{[L]} marker supplies laughter evidence only and is not
by itself a sustained floor take or takeover.
by itself a sustained floor take or takeover. A positive EOT pre-label must
also select one of the supplied opportunity-anchor options.
We use \texttt{deepseek-v4-flash} at temperature zero with a primary and a
skeptical pass. Disagreement on verdict, event type, or hard-negative subtype
produces an \textsc{Unsure} suggestion. Every candidate then receives mandatory
human adjudication: accept the complete pre-label, relabel it, or exclude an
human adjudication: accept the complete pre-label and selected EOT trigger,
relabel it (selecting a displayed trigger for a positive EOT), or exclude an
unscorable region. Only human-confirmed \textsc{EOT-Response},
\textsc{INT-Yield}, and hard-negative opportunities enter evaluation;
\textsc{Not-Applicable}, \textsc{Exclude}, and unresolved candidates do not.