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.

Streaming keyword spotting on mobile devices

Abstract: In this work we explore the latency and accuracy of keyword spotting (KWS) models in streaming and non-streaming modes on mobile phones. NN model conversion from non-streaming mode (model receives the whole input sequence and then returns the classification result) to streaming mode (model receives portion of the input sequence and classifies it incrementally) may require manual model rewriting. We address this by designing a Tensorflow/Keras based library which allows automatic conversion of non-streaming models to streaming ones with minimum effort. With this library we benchmark multiple KWS models in both streaming and non-streaming modes on mobile phones and demonstrate different tradeoffs between latency and accuracy. We also explore novel KWS models with multi-head attention which reduce the classification error over the state-of-art by 10% on Google speech commands data sets V2. The streaming library with all experiments is open-sourced.

Request routing and updating routing information utilizing client location information

Abstract: A system, method, and computer-readable medium for updating request routing information associated with client location information are provided. A content delivery network service provider receives a DNS query from a client computing device The DNS query corresponds to a resource identifier for requested content from the client computing device The content delivery network service provider obtains a query IP address corresponding to the client computing device Based on routing information associated with the query IP address, the content delivery network service provider routes the DNS query The process further includes monitoring performance data associated with the transmission of the requested resource and updating routing information associated with the query IP address based on the performance data for use in processing subsequent requests from the client computing device

System and Method for Filling an Order

Abstract: A method for fulfilling inventory requests includes receiving an inventory request requesting an inventory item and selecting the requested inventory item from an inventory holder. The method further includes storing the requested inventory item in an order holder associated with the inventory request and moving the order holder to a storage space. In addition, the method includes detecting a triggering event and in response to detecting the triggering event, retrieving the order holder from the storage space.

PanPhon: A Resource for Mapping IPA Segments to Articulatory Feature Vectors

Abstract: This paper contributes to a growing body of evidence that—when coupled with appropriate machine-learning techniques–linguistically motivated, information-rich representations can outperform one-hot encodings of linguistic data. In particular, we show that phonological features outperform character-based models. PanPhon is a database relating over 5,000 IPA segments to 21 subsegmental articulatory features. We show that this database boosts performance in various NER-related tasks. Phonologically aware, neural CRF models built on PanPhon features are able to perform better on monolingual Spanish and Turkish NER tasks that character-based models. They have also been shown to work well in transfer models (as between Uzbek and Turkish). PanPhon features also contribute measurably to Orthography-to-IPA conversion tasks.