Audio Representation Learning by Distilling Video as Privileged Information
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Deep audio representation learning using multimodal audiovisual data often leads to a better performance compared to unimodal approaches. However, in real-world scenarios, both modalities are not always available at the time of inference, leading to performance degradation by models trained for multimodal inference. In this article, we propose a novel approach for deep audio representation learning using audiovisual data when the video modality is absent at inference. For this purpose, we adopt teacher–student knowledge distillation under the framework of learning using privileged information (LUPI). While the previous methods proposed for LUPI use soft labels generated by the teacher, in our proposed method, we use <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">embeddings</i> learned by the teacher to train the student network. We integrate our method in two different settings: sequential data where the features are divided into multiple segments throughout time, and nonsequential data where the entire features are treated as one whole segment. In the nonsequential setting, both the teacher and student networks are comprised of an encoder component and a task header. We use the embeddings produced by the encoder component of the teacher to train the encoder of the student, while the task header of the student is trained using ground-truth labels. In the sequential setting, the networks have an additional aggregation component that is placed between the encoder and the task header. We use two sets of embeddings produced by the encoder and the aggregation component of the teacher to train the student. Similar to the nonsequential setting, the task header of the student network is trained using ground-truth labels. We test our framework on two different audiovisual tasks, namely, speaker recognition and speech emotion recognition. Through these experiments, we show that by treating the video modality as privileged information for the main goal of audio representation learning, our method results in considerable improvements over sole audio-based recognition as well as prior works that use LUPI.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.002 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it