Combines learned time-frequency representation with a masker architecture based on 1D [dilated convolution](https://paperswithcode.com/method/dilated-convolution).

InterBERT aims to model interaction between information flows pertaining to different modalities. This new architecture builds multi-modal interaction and preserves the independence of single modal representation. InterBERT is built with an image embedding layer, a text embedding layer, a single-stream interaction module, and a two stream extraction module. The model is pre-trained with three tasks: 1) masked segment modeling, 2) masked region modeling, and 3) image-text matching.

InterBERT

InterBERT: Vision-and-Language Interaction for Multi-modal Pretraining

ConvTasNet

Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation

Represent and associate with a composite of primitive fields.

Source	Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com