Search

Grapheme-to-phoneme (G2P) models are a key component in Automatic Speech Recognition (ASR) systems, such as the ASR system in Alexa, as they are used to generate pronunciations for out-of-vocabulary words that do not exist in the pronunciation lexicons (mappings like "e c h o" to "E k oU"). Most G2P systems are monolingual and based on traditional joint-sequence based n-gram models [1,2]. As an alternative, we present a single end-to-end trained neural G2P model that shares same encoder and decoder across multiple languages. This allows the model to utilize a combination of universal symbol inventories of Latin-like alphabets and cross-linguistically shared feature representations. Such model is especially useful in the scenarios of low resource languages and code switching/foreign words, where the pronunciations in one language need to be adapted to other locales or accents. We further experiment with word language distribution vector as an additional training target in order to improve system performance by helping the model decouple pronunciations across a variety of languages in the parameter space. We show 7.2% average improvement in phoneme error rate over low resource languages and no degradation over high resource ones compared to monolingual baselines., Comment: Published in INTERSPEECH (2019)

Many HPC applications can be expressed as mixed-mode computations, in which each node of a computational DAG is itself a parallel computation that can be molded at runtime to allocate different amounts of processing resources. At the same time, modern HPC systems are becoming increasingly heterogeneous to address the requirements of energy efficiency. Effectively using heterogeneous devices is complex, requiring the developer to be aware of each DAG nodes' criticality, and the relative performance of the underlying heterogeneous resources. This paper studies how irregular mixed-mode parallel computations can be mapped on a single-ISA heterogeneous architecture with the goals of performance and portability. To achieve high performance we analyze various schemes for heterogeneous scheduling, including both criticality-aware and performance-only schemes, and extend them with task molding to dynamically adjust the amount of resources used for each task. To achieve performance portability we track each DAG nodes' performance and construct an online model of the system and its performance. Using a HiKey960 big.LITTLE board as experimental system, the resulting scheduler implementations achieve large speed-ups when executing irregular DAGs compared to traditional random work stealing., Comment: Presented at HIP3ES, 2019. European Commission Project: LEGaTO - Low Energy Toolset for Heterogeneous Computing (EC-H2020-780681)

Hiring credits and employer wage subsidies are tools that policymakers have available to attempt to improve labor market conditions for workers. This study explores how capped-wage subsidies affect firms' labor market decisions, in particular, their reliance on part-time and low-skill workers. We focus on the federal Empowerment Zone program, which offers firms in targeted areas a 20 percent wage subsidy (capped at $3,000 per year) for each employee who also resides in the Empowerment Zone. Results using different methods of identification suggest that firms respond to capped-wage subsidies by expanding their use of part-time workers, particularly where the subsidy cap is likely to bind. We also provide evidence of a shift toward lower-skill workers. [ABSTRACT FROM AUTHOR]