Anuroop Sriram - Academia.edu (original) (raw)

Anuroop Sriram

Related Authors

IEEE/CAA J. Autom. Sinica

Mirco Ravanelli

Mohammad Ali  Zamani

Matiur Rahman Minar

Md Mahadi Hasan  Nahid

Abdelrahman Salem

hm med

Université Libre De Tunis

Uploads

Papers by Anuroop Sriram

Research paper thumbnail of Deep Speech 2 : End-to-End Speech Recognition in English and Mandarin

We show that an end-to-end deep learning approach can be used to recognize either English or Mand... more We show that an end-to-end deep learning approach can be used to recognize either English or Mandarin Chinese speech–two vastly different languages. Because it replaces entire pipelines of hand-engineered components with neural networks , end-to-end learning allows us to handle a diverse variety of speech including noisy environments, accents and different languages. Key to our approach is our application of HPC techniques, enabling experiments that previously took weeks to now run in days. This allows us to iterate more quickly to identify superior archi-tectures and algorithms. As a result, in several cases, our system is competitive with the transcription of human workers when benchmarked on standard datasets. Finally, using a technique called Batch Dispatch with GPUs in the data center , we show that our system can be inexpensively deployed in an online setting, delivering low latency when serving users at scale.

Research paper thumbnail of FRED (A Framework for Reconstructing Epidemic Dynamics): an open-source software system for modeling infectious diseases and control strategies using census-based populations

BMC Public Health, 2013

Background: Mathematical and computational models provide valuable tools that help public health ... more Background: Mathematical and computational models provide valuable tools that help public health planners to evaluate competing health interventions, especially for novel circumstances that cannot be examined through observational or controlled studies, such as pandemic influenza. The spread of diseases like influenza depends on the mixing patterns within the population, and these mixing patterns depend in part on local factors including the spatial distribution and age structure of the population, the distribution of size and composition of households, employment status and commuting patterns of adults, and the size and age structure of schools. Finally, public health planners must take into account the health behavior patterns of the population, patterns that often vary according to socioeconomic factors such as race, household income, and education levels.

Research paper thumbnail of Evaluating Centrality Metrics in Real-World Networks on GPU

GPGPU has received a lot of attention recently as a cost effective solution for high performance ... more GPGPU has received a lot of attention recently as a cost effective solution for high performance computing. In this paper we present a parallel algorithm for computing Betweenness centrality (BC) using CUDA. BC is an important metric in small world network analysis which is expensive to compute. While there are existing parallel implementations, ours is the first implementation on commodity hardware. Our algorithm exploits parallelism at multiple levels of granularity to achieve good performance. We conduct several experiments to show that the algorithm gives considerable speedup over sequential algorithms. We also provide a detailed analysis of the performance of the algorithm.

Research paper thumbnail of Deep Speech 2 : End-to-End Speech Recognition in English and Mandarin

We show that an end-to-end deep learning approach can be used to recognize either English or Mand... more We show that an end-to-end deep learning approach can be used to recognize either English or Mandarin Chinese speech–two vastly different languages. Because it replaces entire pipelines of hand-engineered components with neural networks , end-to-end learning allows us to handle a diverse variety of speech including noisy environments, accents and different languages. Key to our approach is our application of HPC techniques, enabling experiments that previously took weeks to now run in days. This allows us to iterate more quickly to identify superior archi-tectures and algorithms. As a result, in several cases, our system is competitive with the transcription of human workers when benchmarked on standard datasets. Finally, using a technique called Batch Dispatch with GPUs in the data center , we show that our system can be inexpensively deployed in an online setting, delivering low latency when serving users at scale.

Research paper thumbnail of FRED (A Framework for Reconstructing Epidemic Dynamics): an open-source software system for modeling infectious diseases and control strategies using census-based populations

BMC Public Health, 2013

Background: Mathematical and computational models provide valuable tools that help public health ... more Background: Mathematical and computational models provide valuable tools that help public health planners to evaluate competing health interventions, especially for novel circumstances that cannot be examined through observational or controlled studies, such as pandemic influenza. The spread of diseases like influenza depends on the mixing patterns within the population, and these mixing patterns depend in part on local factors including the spatial distribution and age structure of the population, the distribution of size and composition of households, employment status and commuting patterns of adults, and the size and age structure of schools. Finally, public health planners must take into account the health behavior patterns of the population, patterns that often vary according to socioeconomic factors such as race, household income, and education levels.

Research paper thumbnail of Evaluating Centrality Metrics in Real-World Networks on GPU

GPGPU has received a lot of attention recently as a cost effective solution for high performance ... more GPGPU has received a lot of attention recently as a cost effective solution for high performance computing. In this paper we present a parallel algorithm for computing Betweenness centrality (BC) using CUDA. BC is an important metric in small world network analysis which is expensive to compute. While there are existing parallel implementations, ours is the first implementation on commodity hardware. Our algorithm exploits parallelism at multiple levels of granularity to achieve good performance. We conduct several experiments to show that the algorithm gives considerable speedup over sequential algorithms. We also provide a detailed analysis of the performance of the algorithm.

Log In