This work is devoted to presenting a critical assessment by systematically examining complex-valued DNNs against their real-valued counterparts. Specifically, we investigate...
We released the code for our Atlas project [1] on GitHub, as well as pretrained Atlas model checkpoints, an index, and Wikipedia corpora. We present how to build a Q&A system...
We present the SUPERB challenge at SLT 2022, which aims at learning self-supervised speech representation for better performance, generalization, and efficiency.
In this study, we cast the problem of emotion conversion as a spoken language translation task. We use a decomposition of the speech signal into discrete learned representations...
In this work, we frame this problem as a few-shot learning task, and show significant gains with decomposing the task into its "constituent" parts.
In this work, we present a new, more inclusive bias measurement dataset, HOLISTICBIAS, which includes nearly 600 descriptor terms across 13 different demographic axes.
In this work, we present our Joint Audio/Text training method for Transformer Rescorer, to leverage unpaired text-only data which is relatively cheaper than paired audio-text data.
We show that soft-prompt based conditional text generation can be improved with simple and efficient methods that simulate modeling the discourse structure of human written text.
To address this problem, we propose Normalized Contrastive Learning (NCL) which utilizes the Sinkhorn-Knopp algorithm to compute the instance-wise biases that properly normalize...
We show that a dense Lexical Model Λ can be trained to imitate a sparse one, and SPAR is built by augmenting a standard dense retriever with Λ.
