Amazon.com

About: Amazon.com is a company organization based out in Seattle, Washington, United States. It is known for research contribution in the topics: Service (business) & Service provider. The organization has 13363 authors who have published 17317 publications receiving 266589 citations.

Adversarial Auto-encoders for Speech Based Emotion Recognition

Abstract: Recently, generative adversarial networks and adversarial autoencoders have gained a lot of attention in machine learning community due to their exceptional performance in tasks such as digit classification and face recognition. They map the autoencoder's bottleneck layer output (termed as code vectors) to different noise Probability Distribution Functions (PDFs), that can be further regularized to cluster based on class information. In addition, they also allow a generation of synthetic samples by sampling the code vectors from the mapped PDFs. Inspired by these properties, we investigate the application of adversarial autoencoders to the domain of emotion recognition. Specifically, we conduct experiments on the following two aspects: (i) their ability to encode high dimensional feature vector representations for emotional utterances into a compressed space (with a minimal loss of emotion class discriminability in the compressed space), and (ii) their ability to regenerate synthetic samples in the original feature space, to be later used for purposes such as training emotion recognition classifiers. We demonstrate the promise of adversarial autoencoders with regards to these aspects on the Interactive Emotional Dyadic Motion Capture (IEMOCAP) corpus and present our analysis.

Asynchronous task management in an on-demand network code execution environment

Abstract: Systems and methods are described for managing asynchronous code executions in an on-demand code execution system or other distributed code execution environment, in which multiple execution environments, such as virtual machine instances, can be used to enable rapid execution of user-submitted code. When asynchronous executions occur, a first execution may call a second execution, but not immediately need the second execution to complete. To efficiently allocate computing resources, this disclosure enables the second execution to be scheduled accordingly to a state of the on-demand code execution system, while still ensuring the second execution completes prior to the time required by the first execution. Scheduling of executions can, for example, enable more efficient load balancing on the on-demand code execution system.

Audio Albert: A Lite Bert for Self-Supervised Learning of Audio Representation

Abstract: Self-supervised speech models are powerful speech representation extractors for downstream applications. Recently, larger models have been utilized in acoustic model training to achieve better performance. We propose Audio ALBERT, a lite version of the self-supervised speech representation model. We apply the lightweight representation extractor to two downstream tasks, speaker classification and phoneme classification. We show that Audio ALBERT achieves performance comparable with massive pre-trained networks in the downstream tasks while having 91% fewer parameters. Moreover, we design probing models to measure how much the latent representations can encode the speaker’s and phoneme’s information. We find that the representations encoded in internal layers of Audio ALBERT contain more information for both phoneme and speaker than the last layer, which is generally used for downstream tasks. Our findings provide a new avenue for using self-supervised networks to achieve better performance and efficiency.

Fine-grained natural language understanding

Abstract: A system capable of performing natural language understanding (NLU) without the concept of a domain that influences NLU results. The present system uses a hierarchical organizations of intents/commands and entity types, and trained models associated with those hierarchies, so that commands and entity types may be determined for incoming text queries without necessarily determining a domain for the incoming text. The system thus operates in a domain agnostic manner, in a departure from multi-domain architecture NLU processing where a system determines NLU results for multiple domains simultaneously and then ranks them to determine which to select as the result.

The Sockeye 2 neural machine translation toolkit at AMTA 2020

Abstract: We present Sockeye 2, a modernized and streamlined version of the Sockeye neural machine translation (NMT) toolkit. New features include a simplified code base through the use of MXNet's Gluon API, a focus on state of the art model architectures, distributed mixed precision training, and efficient CPU decoding with 8-bit quantization. These improvements result in faster training and inference, higher automatic metric scores, and a shorter path from research to production.