icassp2027-experiment/docs/easycom_event_review_tool.md

EasyCom wearer-entry/INT pre-label and review pipeline

The workflow has three explicit stages. Speech activity timestamps are read-only throughout; reviewed events never modify the dense 5 Hz activity ground truth.

EasyCom participant speech intervals
  -> all wearer boundaries + independent rule regions + structured factual evidence
  -> DeepSeek semantic pre-label (optional but recommended)
  -> human Accept / Relabel / Exclude

1. Generate candidates

Develop the rules on training-side Sessions 4--12:

python3 prepare_easycom_eot_int_review.py \
  --dataset-root /path/to/easycom \
  --sessions Session_4 Session_5 Session_6 Session_7 Session_8 Session_9 Session_10 Session_11 Session_12 \
  --output-dir reports/easycom_floor_event_candidates

The generator emits two independent files:

• easycom_eot_int_candidates.jsonl (legacy-compatible filename) contains every raw wearer 0->1 boundary (WEARER_ONSET, WEARER_ENTRY_CANDIDATE), every raw wearer 1->0 boundary (WEARER_OFFSET, YIELD_CANDIDATE), and hard-negative regions that need no wearer transition: SAME_SPEAKER_PAUSE, OTHER_TO_OTHER, OTHER_BACKCHANNEL, and NON_TAKEOVER_OVERLAP;
• easycom_eot_int_controls.jsonl is retained for file-format compatibility and legacy inputs. The current boundary protocol does not deterministically demote wearer onsets or offsets into this file.

No short-gap merge or takeover heuristic controls wearer-boundary admission. For each raw onset, temporal_evidence stores the previous wearer offset, silence duration, every other-speaker interval intersecting that gap, interval coverage, whether it continues across the onset, transcript, and Target_of_Speech. DeepSeek and the human reviewer decide whether the onset is a genuine entry, within-turn resumption, backchannel, or excluded non-event.

Entry construction searches backward for nearby non-wearer releases as optional context. Every option carries factual flags for intervening wearer activity, intervening other onsets, and activity at the wearer onset; the generator does not declare one a valid conversational cause. Each wearer onset produces exactly one primary row. When present, opportunity_options contains the only release anchors that DeepSeek or a human may optionally select; neither may invent a timestamp.

All wearer onsets and offsets carry the rule-stage value candidate; timing alone is not a semantic positive label. For each offset, the JSON records the wearer activity-run start, nearby other intervals, pre-existing and new-other flags, activity immediately before/after the boundary, strict and configurable 50-ms-tolerant crossing, overlap duration, and subsequent speech onsets. wearer_start < other.start < wearer_offset < other.end is evidence rather than an INT prerequisite. Hard-negative scans are rule hints and still require AI and human review. The JSONL retains candidate source, original event time, participant-level activity, raw durations/gaps/overlap evidence, transcript, and Target_of_Speech when present. Target_of_Speech is annotation assistance only and cannot be a deployable model input.

All heuristic durations are configurable rather than frozen paper rules:

--relation-window-seconds
--same-speaker-pause-max-seconds
--other-handover-max-seconds
--short-vocalization-max-seconds
--continuation-min-seconds
--int-offset-tolerance-seconds

Use --max-candidates 1 for a one-event smoke test. summary.json records the exact configuration and candidate counts. easycom_session_timelines.json stores the read-only participant speech lanes used by the full-session web timeline; it is not sent to DeepSeek.

2. Add DeepSeek pre-labels

Prompt v14 first reconstructs the exact participant-resolved chronology and then uses transcript content and Target_of_Speech to determine conversational function. It treats the EasyCom transcript marker [L] as laughter-only evidence, not as a lexical floor take. Wearer laughter during another participant's retained turn is directed toward ENTRY_WEARER_BACKCHANNEL; non-wearer laughter overlapping a retained wearer turn is directed toward INT_OTHER_BACKCHANNEL. Ambiguous laughter falls back to EXCLUDE, and [L] alone is neither evidence of a floor take nor evidence of a visible smile. Preceding release options are optional entry metadata. No entry/within-turn or INT/takeover semantic decision is made before the prompt. A positive WEARER_ENTRY may optionally select one supplied release; entries from silence or during other activity use null.

needs_human_review is not requested from DeepSeek: every pre-label enters the human queue by protocol, so the adjudicator assigns that boolean locally. This prevents a string-valued model field from invalidating and retrying an otherwise valid batch.

First inspect exactly what would be uploaded:

python3 adjudicate_easycom_eot_int_candidates.py \
  --input reports/easycom_floor_event_candidates/easycom_eot_int_candidates.jsonl \
  --output reports/easycom_floor_event_candidates/easycom_eot_int_deepseek.jsonl \
  --model deepseek-v4-flash \
  --max-events 1 \
  --dry-run

After setting DEEPSEEK_API_KEY and obtaining authorization to upload the candidate excerpts:

python3 adjudicate_easycom_eot_int_candidates.py \
  --input reports/easycom_floor_event_candidates/easycom_eot_int_candidates.jsonl \
  --output reports/easycom_floor_event_candidates/easycom_eot_int_deepseek.jsonl \
  --model deepseek-v4-flash \
  --allow-external-transcript-upload

For SiliconFlow, keep the same API-key environment variable and select its OpenAI-compatible endpoint explicitly:

python3 adjudicate_easycom_eot_int_candidates.py \
  --input reports/easycom_entry_int_sessions1_3_v14/easycom_eot_int_candidates.jsonl \
  --output reports/easycom_entry_int_sessions1_3_v14/easycom_eot_int_deepseek.jsonl \
  --base-url https://api.siliconflow.cn/v1 \
  --model deepseek-ai/DeepSeek-V4-Flash \
  --allow-external-transcript-upload

The default request batch remains 8. If a returned batch violates the strict label schema, the adjudicator isolates the bad record by recursively splitting 8 to 4, 2, and 1. Each successful leaf batch is atomically recorded in OUTPUT.checkpoint.json; rerunning the identical command resumes from that checkpoint and does not request completed passes again. A singleton that still fails after --max-retries is written to OUTPUT_STEM_pending.jsonl for manual relabeling, while the remaining candidates continue. Provider/network failure does not create a semantic pending item: the command stops with its checkpoint intact and the identical command resumes later. Use --checkpoint or --pending-output to override the derived paths. --overwrite intentionally starts a fresh run instead of resuming.

DeepSeek sees candidate source, structured timing, per-speaker activity, and transcript together. It returns one of POSITIVE, HARD_NEGATIVE, or EXCLUDE; positives additionally receive WEARER_ENTRY or INT_YIELD, and hard negatives receive a named subtype. It cannot modify timestamps. The output preserves the original rule candidate, the selected preceding-release UID when applicable, and the complete AI decision/provenance. EXCLUDE is the sole non-scoring outcome, but it is never an untyped bucket. Every AI and human exclusion stores one closed-vocabulary exclude_reason and the derived exclude_reason_group. OUT_OF_SCOPE_* means the annotations are valid but the behavior is outside the scored target; INSUFFICIENT_EVIDENCE means the supplied valid material cannot resolve conversational function; and DATA_* identifies unusable annotation, recording, context, artifact, or timestamp quality. Model-pass disagreement is recorded as INSUFFICIENT_EVIDENCE, never as data corruption.

Hard negatives use behavior-specific subtypes. ENTRY distinguishes a same-other mid-turn pause, a different-other transition, and a wearer backchannel that does not take the floor. INT first distinguishes an other backchannel, then a non-backchannel overlap after which the wearer demonstrably holds or resumes the floor, and finally another interpretable overlap that fails to become a sustained takeover. OTHER_HARD_NEGATIVE is reserved for valid false-positive opportunities outside these named behaviors; it is never an uncertainty fallback. Prompt v16 gives adjacency-pair completion priority over duration: a short but complete answer to an addressed question remains a positive wearer entry, and floor entry does not require the wearer to retain the next turn. Later resumption by the questioner or another speaker therefore does not turn the completed answer into a wearer backchannel. ENTRY_WEARER_BACKCHANNEL is reserved for feedback that does not answer a question, accept or reject a proposal, provide requested information, or otherwise complete an adjacency pair.

The onset and offset of one wearer vocalization remain separate raw boundary candidates, but they are not automatically two scoring opportunities. If the wearer activity run is a backchannel inside a non-wearer's retained turn, its onset may be retained once as ENTRY_WEARER_BACKCHANNEL; its trailing offset is excluded as OUT_OF_SCOPE_WEARER_BACKCHANNEL_OFFSET, rather than being counted again as an INT hard negative. This episode-level interpretation is made by the LLM and human reviewer from timing and transcript evidence, not by candidate-generation gating.

During live adjudication, the CLI displays a dependency-free progress bar over all candidate/pass work, including the current pass, batch, percentage, and elapsed time. Redirected logs emit periodic progress lines instead of carriage return animation.

Every current WEARER_ONSET and WEARER_OFFSET row is sent for semantic adjudication regardless of its timing pattern. Explicit control rows from older protocol files remain excluded unless controls are intentionally reviewed.

3. Human review

Run the web workspace on the AI-enriched JSONL:

python3 review_floor_events.py \
  --dataset-root /path/to/easycom \
  --events reports/easycom_floor_event_candidates/easycom_eot_int_deepseek.jsonl \
  --output reports/easycom_event_reviews/reviews.jsonl

Open http://127.0.0.1:8765. The page shows a session candidate overview, participant activity near the event, video/audio, transcript, structured timing, and the AI verdict/confidence/reason. A decision guide first states the behavioral question, then presents the exact AI verdict/subtype with a plain-language meaning; the Accept control repeats that exact label so its effect is explicit. The common path is one operation:

• Accept keeps the AI verdict/type and optional preceding-release metadata;
• Relabel expands verdict and subtype controls; a positive entry may optionally select one of the supplied release anchors;
• Exclude requires a concrete out-of-scope or data-quality reason.

The current primary-review UI deliberately has no second-review action. Older saved second_review records remain readable for backward compatibility.

Boundary correction is hidden under an optional disclosure and is limited to one 200 ms bin. The original timestamp is always retained. Each save atomically rewrites JSONL and CSV while preserving the rule candidate, AI decision, human decision, relabel flag, exclusion state, confidence, and provenance. The current UI does not ask for a reviewer name; the export retains an empty reviewer field only for compatibility with older review files.

The primary review queue filters only explicit legacy control rows. To audit those controls intentionally, pass --events .../easycom_eot_int_controls.jsonl --include-controls and use a separate review output file. The old --include-offset-controls spelling remains an alias.

Protocol wording for the paper appendix:

Every observed wearer speech onset and offset is retained as a semantic review candidate. Deterministic construction records only participant-resolved timing, transcript, and target-of-speech facts; it does not infer within-turn resumption, floor entry, interruption, or takeover.

Freeze discipline

Develop the guide and resolve disagreements only on Sessions 4--12. Freeze categories and thresholds before reviewing official test Sessions 1--3. Use two independent human review files plus a separate adjudication output for paper- quality labels. DeepSeek is pre-label metadata, not an independent reviewer.