Related papers: Composing Finite State Transducers on GPUs
The performance of graph programs depends highly on the algorithm, the size and structure of the input graphs, as well as the features of the underlying hardware. No single set of optimizations or one hardware platform works well across all…
We propose Neural-FST Class Language Model (NFCLM) for end-to-end speech recognition, a novel method that combines neural network language models (NNLMs) and finite state transducers (FSTs) in a mathematically consistent framework. Our…
Program synthesis is an umbrella term for generating programs and logical formulae from specifications. With the remarkable performance improvements that GPUs enable for deep learning, a natural question arose: can we also implement a…
End-to-end model, especially Recurrent Neural Network Transducer (RNN-T), has achieved great success in speech recognition. However, transducer requires a great memory footprint and computing time when processing a long decoding sequence.…
In this work we evaluate the potential of FPGAs for accelerating HPC workloads as a more power-efficient alternative to GPUs. Using High-Level Synthesis and a large set of optimization techniques, we show that FPGAs can achieve better…
Detecting and extracting textual information from natural scene images needs Scene Text Detection (STD) algorithms. Fully Convolutional Neural Networks (FCNs) are usually utilized as the backbone model to extract features in these instance…
Neural transducers have been widely used in automatic speech recognition (ASR). In this paper, we introduce it to streaming end-to-end speech translation (ST), which aims to convert audio signals to texts in other languages directly.…
This paper presents novel Weighted Finite-State Transducer (WFST) topologies to implement Connectionist Temporal Classification (CTC)-like algorithms for automatic speech recognition. Three new CTC variants are proposed: (1) the…
In this paper, we review various end-to-end automatic speech recognition algorithms and their optimization techniques for on-device applications. Conventional speech recognition systems comprise a large number of discrete components such as…
We present a novel, quadrature-based finite element integration method for low-order elements on GPUs, using a pattern we call \textit{thread transposition} to avoid reductions while vectorizing aggressively. On the NVIDIA GTX580, which has…
This paper introduces a nonlinear string sound synthesizer, based on a finite difference simulation of the dynamic behavior of strings under various excitations. The presented synthesizer features a versatile string simulation engine…
The design of complex Systems-on-Chips implies to take into account communication and memory access constraints for the integration of dedicated hardware accelerator. In this paper, we present a methodology and a tool that allow the…
Schur complement matrices emerge in many domain decomposition methods that can solve complex engineering problems using supercomputers. Today, as most of the high-performance clusters' performance lies in GPUs, these methods should also be…
The rapidly-changing deep learning landscape presents a unique opportunity for building inference accelerators optimized for specific datacenter-scale workloads. We propose Full-stack Accelerator Search Technique (FAST), a hardware…
Simultaneous speech translation (SST) takes streaming speech input and generates text translation on the fly. Existing methods either have high latency due to recomputation of input representations, or fall behind of offline ST in…
The increasing demand of dedicated accelerators to improve energy efficiency and performance has highlighted FPGAs as a promising option to deliver both. However, programming FPGAs in hardware description languages requires long time and…
Self-supervised learning has been proved to benefit a wide range of speech processing tasks, such as speech recognition/translation, speaker verification and diarization, etc. However, most of current approaches are computationally…
Auto-regressive speech-text models pre-trained on interleaved text tokens and discretized speech tokens demonstrate strong speech understanding and generation, yet remain substantially less compute-efficient than text LLMs, partly due to…
Many artificial intelligence (AI) devices have been developed to accelerate the training and inference of neural networks models. The most common ones are the Graphics Processing Unit (GPU) and Tensor Processing Unit (TPU). They are highly…
General-purpose multiprocessors (as, in our case, Intel IvyBridge and Intel Haswell) increasingly add GPU computing power to the former multicore architectures. When used for embedded applications (for us, Synthetic aperture radar) with…