Connectionist Temporal Classification (CTC) is a widely used criterion for training supervised sequence-to-sequence (seq2seq) models. It learns the alignments between the input and output sequences by marginalizing over the perfect alignments (that yield the ground truth), at the expense of the imperfect ones. This dichotomy, and in particular the equal treatment of all perfect alignments, results in a lack of controllability over the predicted alignments. This controllability is essential for capturing properties that hold significance in real-world applications. Here we propose Align With Purpose (AWP), a general Plug-and-Play framework for enhancing a desired property in models trained with the CTC criterion. We do that by complementing the CTC loss with an additional loss term that prioritizes alignments according to a desired property. AWP does not require any intervention in the CTC loss function, and allows to differentiate between both perfect and imperfect alignments for a variety of properties. We apply our framework in the domain of Automatic Speech Recognition (ASR) and show its generality in terms of property selection, architectural choice, and scale of the training dataset (up to 280,000 hours). To demonstrate the effectiveness of our framework, we apply it to two unrelated properties: token emission time for latency optimization and word error rate (WER). For the former, we report an improvement of up to 590ms in latency optimization with a minor reduction in WER, and for the latter, we report a relative improvement of 4.5% in WER over the baseline models. To the best of our knowledge, these applications have never been demonstrated to work on this scale of data. Notably, our method can be easily implemented using only a few lines of code and can be extended to other alignment-free loss functions and to domains other than ASR.

Over the last decade, programmable Network Processors (NPs) have become widely used in Internet routers and other network components. NPs enable rapid development of complex packet processing functions as well as rapid response to changing requirements. In the network research community, the use of NPs has been limited by the challenges associated with learning to program these devices and with using them for substantial research projects. This paper reports on an extension to the Open Network Laboratory testbed that seeks to reduce these "barriers to entry" by providing a complete and highly configurable NP-based router that users can access remotely and use for network experiments. The base router includes support for IP route lookup and general packet filtering, as well as a flexible queueing sub-system and extensive support for performance monitoring. In addition, it provides a plugin environment that can be used to extend the router's functionality, enabling users to carry out significant network experiments with a relatively modest investment of time and effort. This paper describes our NP router and explains how it can be used. We provide several examples of network experiments that have been implemented using the plugin environment, and provide some baseline performance data to characterize the overall system performance. We also report that these routers have already been used for ten non-trivial projects in an advanced architecture course where most of the students had no prior experience using NPs.

In recent years, overlay networks have become an important vehicle for delivering Internet applications. Overlay network nodes are typically implemented using general purpose servers or clusters. We investigate the performance benefits of more integrated architectures, combining general-purpose servers with high performance Network Processor (NP) subsystems. We focus on PlanetLab as our experimental context and report on the design and evaluation of an experimental PlanetLab platform capable of much higher levels of performance than typical system configurations. To make it easier for users to port applications, the system supports a fast path/slow path application structure that facilitates the mapping of the most performance-critical parts of an application onto an NP subsystem, while allowing the more complex control and exception-handling to be implemented within the programmer-friendly environment provided by conventional servers. We report on implementations of two sample applications, an IPv4 router, and a forwarding application for the Internet Indirection Infrastructure. We demonstrate an 80x improvement in packet processing rates and comparable reductions in latency.