Omni-only Turn-Taking Experiment

This project tests whether Qwen2.5-Omni-3B can replace both the handcrafted audio/visual feature extractors and the downstream RNN/Transformer used by EgoSpeak for egocentric turn-taking anticipation.

The main experiment is deliberately simple:

causal audio + video up to time t
                |
                v
     Qwen2.5-Omni-3B Thinker
                |
        fused state q_t [2048]
                |
                v
       trainable prediction head
                |
                v
  future logits [10 horizons, 3 classes]

There is no RNN after Qwen. The Omni Thinker is the temporal model. The only supervised component in the first experiment is a small 10 x 3 classification head.

Current status

File	Status	Purpose
smoke_test.py	Verified on one NVIDIA L20	Text and 12-second EasyCom audio-video inference
easycom_manifest.py	Implemented, awaiting dataset-side run	Discover one-minute clips, preserve session timecodes, and check 5 Hz targets
qwen_omni_features.py	Implemented, not executed here	Load only the 3B Thinker and extract fused states from one AV window
streaming_turn_model.py	Prototype implemented, not executed here	Produce one causal Omni state every 200 ms, with reference and KV-cache modes
TurnPredictionHead	Defined, untrained	Map [2048] to [10, 3] logits
Head training and EgoSpeak evaluation script	Not yet implemented	Align saved states with target_perframe, train the head, and reproduce Table 2 mAP

The official full model, Thinker input path, embedded audio, video decoding, and FlashAttention-2 have passed a 12-second EasyCom smoke test on one NVIDIA L20. Streaming extraction, cache equivalence, target alignment, training, and paper metrics remain unverified.

Why Omni-only instead of Omni + RNN

EgoSpeak separately extracts visual and audio features and then uses GRU, LSTR, or Mamba for temporal modeling:

ResNet50 video feature + wav2vec2 audio feature -> temporal model -> prediction

Qwen2.5-Omni already contains:

• audio and visual encoders;
• joint audio-video temporal positions;
• a causal decoder-only Thinker with KV cache;
• pretrained acoustic, visual, and semantic knowledge.

Adding a GRU after a continuously processed Omni sequence would model history twice and would make it harder to attribute an improvement to Omni. The primary comparison is therefore:

EgoSpeak: ResNet50 + wav2vec2 + GRU
Ours:     Qwen2.5-Omni Thinker + small prediction head

An Omni-feature-plus-GRU model can be kept as an ablation, but it is not the main architecture.

EgoSpeak contract that this project reproduces

The inspected reference repository is /Volumes/760P/Code/EgoSpeak. It contains no Qwen or Omni implementation and no raw-media feature extraction scripts. It distributes precomputed arrays instead:

DATASET/
|- rgb_kinetics_resnet50/   # [T, 2048]
|- audio_wav2vec2/          # [T, 5120]
`- target_perframe/         # [T, 3]

The useful part for this project is the exact task interface.

Time and classes

Both EasyCom and the EgoSpeak EGO4DSHUFFLE split use 5 FPS, so one task timestep is 0.2 seconds. The three output columns are:

0: background
1: camera wearer speaking
2: other people speaking

They are not strictly one-hot. Background is exclusive, but simultaneous camera-wearer and other-person speech is stored as [0, 1, 1]. The inspected EasyCom features contain 7,711 such overlap steps. Preserve the full multi-positive target rather than applying argmax.

Relevant EgoSpeak files:

• LSTR/data/data_info.json: FPS, classes, and session splits;
• MiniROAD/configs/EasyCom/miniroad_aa_easycom.yaml: 128-step training windows, stride 4, three classes, and anticipation length 10;
• MiniROAD/datasets/dataset.py: feature loading and future-label indexing;
• MiniROAD/criterions/loss.py: anticipation loss;
• MiniROAD/trainer/eval.py: per-horizon AP and mean anticipation mAP.

Future target alignment

For current task index i, the prediction target is:

target[i + 1 : i + 11]

Thus the ten output rows represent:

t+0.2, t+0.4, t+0.6, ..., t+2.0 seconds

If states[i] is verified to correspond to EgoSpeak task index i, the offline head-training tensors should be constructed as follows:

target = target_perframe                            # [T, 3], multi-positive
usable = min(len(states), len(target)) - 10

x = states[:usable]                                 # [N, 2048]
y = stack(
    [target[h : h + usable] for h in range(1, 11)],
    axis=1,
)                                                   # [N, 10, 3]

Do not silently assume that the first saved Omni state matches label index zero. EgoSpeak does not publish the script that generated its original ResNet/wav2vec2 features, so the exact zero-time convention is not documented. Before training, inspect a short clip with known speech boundaries and test the candidate mappings states[i] -> target[i] and states[i] -> target[i+1]. Store the selected offset in every feature file/checkpoint.

Splits

Use the published split, not a random frame split.

EasyCom:

• train, preserving EgoSpeak's list: Session_7, Session_11, Session_10, Session_6, Session_9, Session_4, Session_8, Session_5, Session_12;
• test, preserving EgoSpeak's list: Session_3, Session_2, Session_1.

This is the EgoSpeak comparison split. The EasyCom dataset repository itself recommends a different train/validation/test split; do not substitute that split when reproducing EgoSpeak Table 2.

Ego4D Audio-Visual Diarization:

• use the EGO4DSHUFFLE key;
• 346 training clips;
• 87 test clips;
• each clip is approximately five minutes.

Never mix timesteps from the same session across training and validation.

EasyCom raw-media layout and manifest

The extracted release used here has this relevant structure:

extracted_easycom/
`- Main/
   |- Video_Compressed/
   |  |- Session_1/
   |  |  |- 00-00-000.mp4
   |  |  |- 01-00-000.mp4
   |  |  `- ...
   |  `- Session_2 ... Session_12/
   |- Glasses_Microphone_Array_Audio/
   |- Close_Microphone_Audio/
   |- Speech_Transcriptions/
   `- Metadata/

Video_Compressed is the AR-glasses wearer's egocentric stream with embedded stereo AAC audio. Each session is divided into approximately one-minute clips; the mm-ss-SSS filename is the clip's start time on the original recording timeline. Some intervals are absent because EasyCom redacted one-minute segments. These raw time gaps are expected.

EgoSpeak does not preserve those empty intervals. Its appendix states that it crops every EasyCom clip to retain only the 1920-pixel-wide video region and then merges the retained clips into one dense video per session. Therefore the EgoSpeak-compatible label time for a clip is its cumulative position in the concatenation, not the mm-ss-SSS source time. The manifest stores both.

Build a raw-video manifest and, when the EgoSpeak labels are available, check their duration at 5 Hz:

python easycom_manifest.py \
  --dataset-root /data1/yfzx/wangx/Datasets/easycom/extracted_easycom \
  --target-root /path/to/EasyCom/target_perframe \
  --output manifests/easycom.json

Omit --target-root for the first media-only inventory. The manifest reports raw-source discontinuities as informational and computes each clip's dense EgoSpeak concatenation offset and corresponding 5 Hz target index. For the audio-only ablation, use the same embedded glasses audio as A+V (extract it to mono WAV if needed); do not switch to close microphones, because that changes the sensor and makes the modality ablation unfair.

Audit downloaded EgoSpeak arrays, and optionally compare every session length against the raw manifest:

python audit_egospeak_features.py \
  --feature-root /path/to/EgoSpeak/dataset/EasyCom \
  --raw-manifest manifests/easycom.json \
  --output reports/egospeak_easycom_audit.json

The inspected release contains 95,453 synchronized steps across all 12 sessions: 5.302944 hours at 5 Hz. Every session has identical RGB, flow, audio, and target length. Shapes are [T,2048], [T,2048], [T,5120], and [T,3].

Recommended comparison matrix

Experiment	Visual sampling	Audio	Output rate
EgoSpeak official A+V	5 Hz ResNet features	5 Hz wav2vec2 features	5 Hz
Omni audio-only	none	raw glasses-wearer waveform	5 Hz
Omni A+V primary	2 FPS	raw embedded waveform	5 Hz
Omni A+V FPS ablation	5 FPS	raw embedded waveform	5 Hz

Two FPS is the primary Omni setting because it matches Qwen's default video sampling and permits longer context. Five FPS is the visual-rate ablation. Input feature rates need not match EgoSpeak; the split, causal prediction times, three classes, ten target horizons, and evaluator must match exactly.

Prepare an EgoSpeak-compatible EasyCom session

Do not pass the raw one-minute files independently to Omni and do not preserve the gaps implied by their filenames. EgoSpeak concatenates the retained clips into a dense session timeline and crops the participant-ID banner on the left.

prepare_easycom_session.py reproduces this policy and creates videos whose stored frames already lie on a fixed session-global 2 FPS or 5 FPS grid. This prevents Qwen's per-window video loader from choosing a new adaptive set of frames for every overlapping prefix.

Session 1 has been checked against the local release:

24 retained clips
27,768 source frames at 20 FPS
/ 4 frames per task step
= 6,942 steps at 5 Hz
= target_perframe/Session_1.npy length exactly

Preview the commands and validate frames against the target without encoding:

python prepare_easycom_session.py \
  --session-dir /Volumes/MX500B/Code/easycom/Main/Video_Compressed/Session_1 \
  --output-dir prepared_easycom/Session_1 \
  --target /Volumes/MX500B/Code/EgoSpeak/dataset/EasyCom/target_perframe/Session_1.npy \
  --fps 2 5 \
  --dry-run

Remove --dry-run to run FFmpeg. The outputs are:

Session_1_2fps.mp4     primary Omni A+V input
Session_1_5fps.mp4     visual-rate ablation
Session_1.json         clip order, exact T, crop and sampling provenance
Session_1.ffconcat     reproducible dense concatenation order

The script fails rather than silently padding or truncating when sum(source_frames) / 4 != target.shape[0].

Each clip's decoded video and audio are trimmed to the exact duration implied by its video frame count before concatenation. This prevents AAC priming/tail padding from accumulating at the 24 clip boundaries and causing progressive audio/video drift.

On the remote L20 machine, use its own dataset paths. For example:

python prepare_easycom_session.py \
  --session-dir /data1/yfzx/wangx/Datasets/easycom/extracted_easycom/Main/Video_Compressed/Session_1 \
  --output-dir /data1/yfzx/wangx/Datasets/easycom/omni_prepared/Session_1 \
  --target /path/to/EgoSpeak/dataset/EasyCom/target_perframe/Session_1.npy \
  --fps 2 5

This is the command that performs the potentially long FFmpeg processing; it has not been run by the code authoring workflow.

If encoding completed but a later validation/metadata step failed, update the script and reuse the existing MP4 without encoding it again:

python prepare_easycom_session.py ... --fps 2 --reuse-existing

What Qwen's native 2-second chunk means

Qwen2.5-Omni is not restricted to receiving audio once every two seconds. It can receive an arbitrary-duration AV input. The two-second value describes internal processing:

1. the audio encoder divides acoustic features into approximately two-second attention blocks;
2. audio and video tokens are interleaved in two-second temporal groups before entering the Thinker.

The audio encoder attention inside a block is non-causal. Therefore this is invalid for online evaluation:

encode the complete [0, 2.0 s] block
-> read a purported state at 0.2 s

That early state can contain audio from 0.2--2.0 seconds. At prediction time t, the model must receive only audio and video with timestamps <= t.

Causal 5 Hz extraction modes

streaming_turn_model.py implements three modes.

1. causal-prefix: correctness and semantic baseline

At every 200 ms, independently process the causal context ending at the current time:

[max(0, t-20 s), t] AV -> Omni -> q_t

Properties:

• strict no-future input;
• one continuous media window per prediction;
• no cross-forward cache;
• very expensive because overlapping context is recomputed;
• preferred reference when checking semantics and causality.

Example:

python streaming_turn_model.py \
  --video /path/to/easycom_session.mp4 \
  --use-audio-in-video \
  --mode causal-prefix \
  --start 0 \
  --end 20 \
  --memory-seconds 20 \
  --output features/easycom_20s_prefix.pt

2. commit-replay: closed-turn compatibility baseline

The extractor retains Thinker KV for completed two-second media blocks. During the unfinished block it branches from the same committed cache and evaluates only the available prefix:

committed historical KV + current block [0.0, 0.2] -> q_t
committed historical KV + current block [0.0, 0.4] -> q_t
...
committed historical KV + current block [0.0, 2.0] -> q_t
                                                    -> commit media KV

The temporary readout/assistant query is never committed. Only the completed media block enters long-term cache. This avoids recomputing the full history, but still re-encodes at most the current two-second prefix.

Example with numerical checking:

python streaming_turn_model.py \
  --video /path/to/easycom_session.mp4 \
  --use-audio-in-video \
  --mode commit-replay \
  --start 0 \
  --end 20 \
  --memory-seconds 20 \
  --verify-every 5 \
  --verify-continuous-every 5 \
  --output features/easycom_20s_stream.pt

--verify-every 5 compares cached processing with a from-scratch replay of the same sequence of two-second media turns. The saved cosine similarity should be extremely close to 1. If it is not, the TMRoPE/cache path is invalid and must not be used for a paper result.

--verify-continuous-every 5 is a different check: it compares the cached sequence of two-second media turns with a single continuous causal window. This comparison need not be numerically identical, but it measures whether the input organization materially changes the representation. Save and report the two check types separately (cache_replay and continuous_window_semantics).

There is an important experimental distinction: commit-replay represents history as a sequence of two-second media turns. Its numerical check proves cache equivalence to that same turn sequence, not equivalence to one continuous 20-second video placeholder. Compare it against causal-prefix on identical clips and report the representation if it changes mAP.

3. open-stream-replay: recommended efficient mode

This mode keeps one user/media turn open across the whole bounded-memory segment. The first block contributes the chat and AV opening markers once; later completed two-second blocks contribute only interleaved audio/video payload tokens:

open AV prefix
  completed [0,2] payload       -> commit KV
  current   [2,2.2] payload     -> temporary branch -> close/read q_t
  current   [2,2.4] payload     -> temporary branch -> close/read q_t
  ...
  completed [2,4] payload       -> commit KV
AV/chat closure                 -> never committed; readout branch only

The audio encoder accepts a shorter final chunk with padding and an actual-length mask. For the two-frame visual patch requirement, strict-grid mode duplicates only the most recent past frame when necessary.

Run a four-second validation before using it for extraction:

python streaming_turn_model.py \
  --model-id /path/to/Qwen2.5-Omni-3B \
  --video prepared_easycom/Session_1/Session_1_2fps.mp4 \
  --use-audio-in-video \
  --mode open-stream-replay \
  --start 0 --end 4 \
  --video-fps 2 \
  --strict-fixed-video-grid \
  --verify-every 5 \
  --verify-continuous-every 5 \
  --flash-attention-2 \
  --output features/Session_1_open_first_4s.pt

cache_replay must be identical to replaying the same open stream from an empty cache. continuous_window_semantics compares it with one normal continuous Qwen AV input. Do not assume equivalence: the modality encoders are still invoked per tail block in the efficient path, so this numerical check is required even though artificial user-turn boundaries have been removed.

Whole-session prediction and the 20-second limit

Twenty seconds is a practical memory/context setting for the 3090, not the maximum video duration. The complete session is processed sequentially and a prediction is emitted every 0.2 seconds.

The legacy commit-replay prototype resets Thinker KV at each non-overlapping 20-second boundary:

session:  0 -------- 20 -------- 40 -------- 60 ...
cache:   [segment 1] [segment 2] [segment 3] ...
output:   continuous predictions across the entire session

This preserves complete output coverage but limits available history after a reset. Report the memory length and additionally evaluate the first two seconds after each reset versus all other timesteps. Rolling KV eviction is a possible future optimization, but requires correct multimodal position rebasing.

open-stream-replay instead uses blockwise rolling memory. With a 20-second budget it rebuilds the open cache from the latest nine completed blocks (18 seconds) when a new block starts, then adds the current 0--2 second tail. Its effective history therefore varies from 18 to 20 seconds and never drops to an empty 0.2-second context at a 20-second boundary.

For the paper experiment, drive the output length from the preparation sidecar rather than a floating MP4 duration:

python streaming_turn_model.py \
  --session-metadata prepared_easycom/Session_1/Session_1.json \
  --use-audio-in-video \
  --mode open-stream-replay \
  --memory-seconds 20 \
  --video-fps 2 \
  --strict-fixed-video-grid \
  --verify-every 25 \
  --verify-continuous-every 25 \
  --output features/Session_1_omni_2fps.pt

The sidecar selects the matching fixed-FPS MP4 and sets N to its exact num_steps. Alternatively pass --video ... --target ... explicitly. A raw 20 FPS MP4 with --video-fps 2 is rejected when --strict-fixed-video-grid is enabled.

In strict A+V mode the extractor does not delegate temporal frame selection to the generic video utility. It reads the already-fixed MP4 grid explicitly, uses only frames with timestamps <= t, and duplicates the most recent past frame when the visual tower needs an even frame count. Audio is loaded once at 16 kHz and sliced exactly at each causal boundary. The processor still receives use_audio_in_video=True, so Qwen's audio/video token interleaving is retained.

Before a full session, run only the first four seconds and inspect both check types:

python streaming_turn_model.py \
  --model-id /data1/yfzx/wangx/Models/Qwen2.5-Omni-3B \
  --video /data1/yfzx/wangx/Datasets/easycom/omni_prepared/Session_1/Session_1_2fps.mp4 \
  --use-audio-in-video \
  --mode open-stream-replay \
  --start 0 --end 4 \
  --video-fps 2 \
  --strict-fixed-video-grid \
  --verify-every 5 \
  --verify-continuous-every 5 \
  --flash-attention-2 \
  --output features/Session_1_first_4s_check.pt

Do not launch all sessions unless cache_replay cosine is nearly 1. The continuous_window_semantics cosine answers a different question and may be lower because media-turn boundaries change the representation.

Video can be sampled at 2 FPS while predictions remain at 5 Hz. Audio and the causal boundary update every 200 ms; consecutive prediction times may use the same most-recent visual frame. A frame with timestamp later than t must never be included.

Saved streaming tensors

Each .pt file contains:

• times: [N], prediction times in seconds;
• states: [N, 2048], causal fused Thinker states;
• label_indices: [0, ..., N-1], direct target_perframe row alignment;
• valid_10_horizon_steps: N-10, because the last ten current rows do not have all future labels;
• mode: causal-prefix, commit-replay, or open-stream-replay;
• stream_representation: explicit input-organization metadata;
• config: step, native block, memory, FPS, and pixel settings;
• verification: cached-versus-exact numerical checks;
• input_video_fps and video_sampling_grid: sampling provenance;
• logits: optional [N, 10, 3] output if a trained head is supplied;
• probabilities: optional softmax probabilities.

Training the 10 x 3 head

The head must be trained. It is not part of pretrained Qwen.

The first experiment should freeze all Qwen parameters and train only:

LayerNorm(2048)
-> Linear(2048, 1024)
-> GELU
-> Dropout
-> Linear(1024, 30)
-> reshape [10, 3]

streaming_turn_model.py exposes:

from streaming_turn_model import (
    TurnPredictionHead,
    egospeak_multihorizon_loss,
)

Recommended initial procedure:

1. Freeze Qwen and extract all training-session states offline.
2. Verify state/label time offset and truncate only the final ten invalid current positions.
3. Keep EgoSpeak targets as float multi-positive tensors [N, 10, 3]; never convert them with argmax.
4. Train with egospeak_multihorizon_loss. It exactly mirrors MiniROAD's anticipation objective: L2-normalize each three-class target, then compute its weighted negative log-softmax.
5. Select hyperparameters using only training sessions. For EasyCom, reserve a training session for development or use session-level cross-validation; never tune on Sessions 1--3.
6. After choosing the epoch/hyperparameters, optionally retrain on all nine EasyCom training sessions and evaluate the fixed model once on the test set.

Class-balanced/focal loss, a learned turn-query token, and LoRA are later ablations. They should not replace the frozen-Omni linear/MLP-head baseline.

EgoSpeak-compatible evaluation

For every valid current timestep, produce probabilities shaped:

[number of timesteps, 10 future horizons, 3 classes]

Then reproduce EgoSpeak's Table 2 procedure:

1. for each horizon independently, concatenate test-session predictions and ground truth;
2. compute per-class frame-level average precision;
3. average the three class AP values to obtain horizon mAP;
4. report all ten horizon mAP values;
5. average the ten horizon mAP values for the final score.

With EgoSpeak's ignore_index=-100, the released evaluator does not remove class index zero, so background is included. Reuse the same implementation or verify a reimplementation numerically.

Reference Table 2 targets from the EgoSpeak paper:

• EasyCom GRU A+V: 60.6 mean mAP;
• EasyCom Transformer A+V: 58.7 mean mAP;
• Ego4D Transformer audio: 69.2 mean mAP;
• Ego4D Transformer A+V: 69.0 mean mAP;
• Ego4D GRU audio: 69.2 mean mAP;
• Ego4D GRU A+V: 68.2 mean mAP.

Do not compare these numbers with EgoSpeak Table 3 target-speaker-only AP; Table 3 uses a different metric.

Experiments that demonstrate Omni's semantic advantage

The headline comparison alone cannot establish that improvements come from semantics. Run the following controlled experiments:

1. Omni audio vs Omni audio+video: measure whether visual grounding helps.
2. Per-horizon curve: semantic completion should be especially visible at longer horizons such as 1.2--2.0 seconds.
3. Context length: compare 4, 10, 15, and 20 seconds without adding an RNN.
4. Layer ablation: compare audio-encoder output and several Thinker layers, because an intermediate layer may be more discriminative than the final generation-oriented layer.
5. Semantic-completion subset: contrast completed utterances with hesitation/incomplete pauses while matching pause duration and basic prosody as closely as possible.
6. Question/statement/backchannel subsets: report target-speaker AP and premature-interruption rate on linguistically meaningful events.
7. Causal transcript baseline: compare Omni audio with causal ASR text plus a language model to isolate lexical/semantic contribution.

The frozen-Omni head is the cleanest representation test. LoRA can be reported as a second-stage ceiling, not as the only result.

Single-window feature inspection

qwen_omni_features.py is useful for inspecting a short window or layer, but it is not the main whole-session experiment.

If audio is embedded in the video:

python qwen_omni_features.py \
  --video /path/to/window.mp4 \
  --use-audio-in-video \
  --output features/window.pt

If audio and video are separate:

python qwen_omni_features.py \
  --video /path/to/window.mp4 \
  --audio /path/to/window.wav \
  --output features/window.pt

Do not provide the same audio both as a separate file and via --use-audio-in-video.

Saved single-window fields are:

• token_features: [B, token_length, 2048];
• last_token: [B, 2048];
• tail_mean: [B, 2048];
• attention_mask: valid-token mask.

Installation

Install ffmpeg, then:

pip install -r requirements.txt

The implementation is pinned to transformers==4.52.3 because the commit/replay path uses version-specific Thinker internals. On Linux, qwen-omni-utils[decord] is recommended for faster video decoding. On a compatible NVIDIA GPU, optionally install flash-attn and pass --flash-attention-2.

Ego4D Audio-Visual Diarization download

Do not download the complete Ego4D release for this experiment. Download only the compressed Audio-Visual Diarization benchmark clips and annotations:

ego4d \
  --output_directory=/path/to/ego4d \
  --datasets clips annotations \
  --benchmarks AV

The approximately 1 TB figure on the Ego4D download page refers to all benchmark clips combined, not only the AV subset. The annotated AVD subset has about 572 five-minute clips (roughly 50 hours). EgoSpeak uses a custom 346/87 train/test split, about 36.1 hours total. Reproducing its Table 2 requires the exact IDs in EgoSpeak's EGO4DSHUFFLE split.

Required validation before a full run

Do not launch full EasyCom/Ego4D extraction until all of these pass:

• no input audio sample or video frame has timestamp later than prediction time t;
• states and target_perframe lengths/time origins are reconciled and the chosen label offset is saved;
• commit/replay cosine equivalence is near 1 on short clips;
• commit/replay and causal-prefix predictions are compared on identical clips;
• a 20-second run fits the 3090 with the selected pixel budget and attention implementation;
• saved outputs contain exactly ten future horizons in the order 0.2--2.0 s;
• the local metric reproduces EgoSpeak's evaluator on known predictions;
• test session IDs never enter training, validation, normalization statistics, or hyperparameter selection.

Once these checks pass, the first publishable experiment is:

frozen Qwen2.5-Omni-3B Thinker
+ trained 10x3 head
+ 20-second causal memory
+ full-session 5 Hz output
+ exact EgoSpeak split and Table 2 metric