Explore the latest research from Facebook

All Publications

January 22, 2022 Wenlei He, Julián Mestre, Sergey Pupyrev, Lei Wang, Hongtao Yu
Paper

Profile Inference Revisited

In this paper we tackle the problem, which is also known as profile inference and profile rectification. We investigate the classical approach for profile inference, based on computing minimum-cost maximum flows in a control-flow graph, and develop an extended model capturing the desired properties of real-world profiles.
Paper
January 16, 2022 Azalea Raad, Josh Berdine, Derek Dreyer, Peter O'Hearn
Paper

Concurrent Incorrectness Separation Logic

Here, we develop concurrent incorrectness separation logic (CISL), which extends ISL to account for bug catching in concurrent programs.
Paper
January 9, 2022 Xiaohui Zhang, Frank Zhang, Chunxi Liu, Kjell Schubert, Julian Chan, Pradyot Prakash, Jun Liu, Ching-Feng Yeh, Fuchun Peng, Yatharth Saraf, Geoffrey Zweig
Paper

Benchmarking LF-MMI, CTC and RNN-T Criteria for Streaming ASR

In this work, to measure the accuracy and efficiency for a latency-controlled streaming automatic speech recognition (ASR) application, we perform comprehensive evaluations on three popular training criteria: LF-MMI, CTC and RNN-T.
Paper
December 16, 2021 Siying Dong, Andrew Kryczka, Yanqin Jin, Michael Stumm
Paper

RocksDB: Evolution of Development Priorities in a Key-value Store Serving Large-scale Applications

We describe how the priorities evolved over time as a result of hardware trends and extensive experiences running RocksDB at scale in production at a number of organizations: from optimizing write amplification, to space amplification, to CPU utilization.
Paper
December 14, 2021 Donglai Xiang, Fabián Prada, Timur Bagautdinov, Weipeng Xu, Yuan Dong, He Wen, Jessica Hodgins, Chenglei Wu
Paper

Modeling Clothing as a Separate Layer for an Animatable Human Avatar

We then train a new two-layer codec avatar with separate modeling of the upper clothing and the inner body layer. To learn the interaction between the body dynamics and clothing states, we use a temporal convolution network to predict the clothing latent code based on a sequence of input skeletal poses. We show photorealistic animation output for three different actors, and demonstrate the advantage of our clothed-body avatars over the single-layer avatars used in previous work.
Paper
December 13, 2021 Konstantinos Vougioukas, Stavros Petridis, Maja Pantic
Paper

DINO: A Conditional Energy-based GAN for Domain Translation

We propose an alternative method for conditioning and present a new framework, where two networks are simultaneously trained, in a supervised manner, to perform domain translation in opposite directions.
Paper
December 13, 2021 Vimal Manohar, Tatiana Likhomanenko, Qiantong Xu, Wei-Ning Hsu, Ronan Collobert, Yatharth Saraf, Geoffrey Zweig, Abdelrahman Mohamed
Paper

Kaizen: Continuously Improving Teacher Using Exponential Moving Average For Semi-supervised Speech Recognition

In this paper, we introduce the Kaizen framework that uses a continuously improving teacher to generate pseudo-labels for semi-supervised speech recognition (ASR). The proposed approach uses a teacher model which is updated as the exponential moving average (EMA) of the student model parameters.
Paper
December 10, 2021 Yangyang Xia, Buye Xu, Anurag Kumar
Paper

Incorporating Real-world Noisy Speech in Neural-network-based Speech Enhancement Systems

In this paper, we explore methods that enable supervised speech enhancement systems to train on real-world degraded speech data. Specifically, we propose a semi-supervised approach for speech enhancement in which we first train a modified vector-quantized variational autoencoder that solves a source separation task.
Paper
December 9, 2021 Alexei Baevski, Wei-Ning Hsu, Alexis Conneau, Michael Auli
Paper

Unsupervised Speech Recognition

This paper describes wav2vec-U, short for wav2vec Unsupervised, a method to train speech recognition models without any labeled data.
Paper
December 9, 2021 Benjamin Aubin, Agnieszka Słowik, Martin Arjovsky, Léon Bottou, David Lopez-Paz
Paper

Linear unit-tests for invariance discovery

The purpose of this note is to propose six linear low-dimensional problems—“unit tests”—to evaluate out-of-distribution generalization algorithms.
Paper