English
Related papers

Related papers: Decoding with Finite-State Transducers on GPUs

200 papers

Weighted finite-state transducers (FSTs) are frequently used in language processing to handle tasks such as part-of-speech tagging and speech recognition. There has been previous work using multiple CPU cores to accelerate finite state…

Computation and Language · Computer Science 2018-05-17 Arturo Argueta , David Chiang

We present an optimized weighted finite-state transducer (WFST) decoder capable of online streaming and offline batch processing of audio using Graphics Processing Units (GPUs). The decoder is efficient in memory utilization, input/output…

Computation and Language · Computer Science 2020-02-17 Hugo Braun , Justin Luitjens , Ryan Leary , Tim Kaldewey , Daniel Povey

We describe initial work on an extension of the Kaldi toolkit that supports weighted finite-state transducer (WFST) decoding on Graphics Processing Units (GPUs). We implement token recombination as an atomic GPU operation in order to fully…

Computation and Language · Computer Science 2018-07-30 Zhehuai Chen , Justin Luitjens , Hainan Xu , Yiming Wang , Daniel Povey , Sanjeev Khudanpur

Finite-state automata are a very effective tool in natural language processing. However, in a variety of applications and especially in speech precessing, it is necessary to consider more general machines in which arcs are assigned weights…

Computation and Language · Computer Science 2007-05-23 Mehryar Mohri , Fernando Pereira , Michael Riley

Speech processing requires very efficient methods and algorithms. Finite-state transducers have been shown recently both to constitute a very useful abstract model and to lead to highly efficient time and space algorithms in this field. We…

cmp-lg · Computer Science 2008-02-03 Mehryar Mohri , Michael Riley , Richard Sproat

We introduce a framework for automatic differentiation with weighted finite-state transducers (WFSTs) allowing them to be used dynamically at training time. Through the separation of graphs from operations on graphs, this framework enables…

Machine Learning · Computer Science 2020-10-05 Awni Hannun , Vineel Pratap , Jacob Kahn , Wei-Ning Hsu

Finite-state transducers (FSTs) are frequently used in speech recognition. Transducer composition is an essential operation for combining different sources of information at different granularities. However, composition is also one of the…

Computation and Language · Computer Science 2021-10-07 Shubho Sengupta , Vineel Pratap , Awni Hannun

This paper describes the conversion of a Hidden Markov Model into a sequential transducer that closely approximates the behavior of the stochastic model. This transformation is especially advantageous for part-of-speech tagging because the…

cmp-lg · Computer Science 2008-02-03 Andre Kempe

The vast majority of inference time for RNN Transducer (RNN-T) models today is spent on decoding. Current state-of-the-art RNN-T decoding implementations leave the GPU idle ~80% of the time. Leveraging a new CUDA 12.4 feature, CUDA graph…

Machine Learning · Computer Science 2024-06-07 Daniel Galvez , Vladimir Bataev , Hainan Xu , Tim Kaldewey

Many research works have been performed on implementation of Vitrerbi decoding algorithm on GPU instead of FPGA because this platform provides considerable flexibility in addition to great performance. Recently, the recently-introduced…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-11-30 Alireza Mohammadidoost , Matin Hashemi

This paper describes a parallel implementation of Viterbi decoding algorithm. Viterbi decoder is widely used in many state-of-the-art wireless systems. The proposed solution optimizes both throughput and memory usage by applying…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-11-19 Alireza Mohammadidoost , Matin Hashemi

Transformers are ubiquitous models in the natural language processing (NLP) community and have shown impressive empirical successes in the past few years. However, little is understood about how they reason and the limits of their…

Computation and Language · Computer Science 2024-03-18 Michael Rizvi , Maude Lizaire , Clara Lacroce , Guillaume Rabusseau

We present a general framework based on weighted finite automata and weighted finite-state transducers for describing and implementing speech recognizers. The framework allows us to represent uniformly the information sources and data…

cmp-lg · Computer Science 2008-02-03 Fernando C. N. Pereira , Michael D. Riley

The transducer architecture is becoming increasingly popular in the field of speech recognition, because it is naturally streaming as well as high in accuracy. One of the drawbacks of transducer is that it is difficult to decode in a fast…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-02 Wei Kang , Liyong Guo , Fangjun Kuang , Long Lin , Mingshuang Luo , Zengwei Yao , Xiaoyu Yang , Piotr Żelasko , Daniel Povey

Many graph algorithms can be viewed as sets of rules that are iteratively applied, with the number of iterations dependent on the size and complexity of the input graph. Existing machine learning architectures often struggle to represent…

Artificial Intelligence · Computer Science 2024-08-21 Florian Grötschla , Joël Mathys , Christoffer Raun , Roger Wattenhofer

While Connectionist Temporal Classification (CTC) models deliver state-of-the-art accuracy in automated speech recognition (ASR) pipelines, their performance has been limited by CPU-based beam search decoding. We introduce a GPU-accelerated…

Audio and Speech Processing · Electrical Eng. & Systems 2023-11-10 Daniel Galvez , Tim Kaldewey

This paper addresses issues in part of speech disambiguation using finite-state transducers and presents two main contributions to the field. One of them is the use of finite-state machines for part of speech tagging. Linguistic and…

cmp-lg · Computer Science 2007-05-23 Evelyne Tzoukermann , Dragomir R. Radev

This paper introduces a highly efficient greedy decoding algorithm for Transducer-based speech recognition models. We redesign the standard nested-loop design for RNN-T decoding, swapping loops over frames and labels: the outer loop…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-20 Vladimir Bataev , Hainan Xu , Daniel Galvez , Vitaly Lavrukhin , Boris Ginsburg

Recurrent Neural Network Language Models (RNNLMs) have started to be used in various fields of speech recognition due to their outstanding performance. However, the high computational complexity of RNNLMs has been a hurdle in applying the…

Computation and Language · Computer Science 2020-07-24 Kyungmin Lee , Chiyoun Park , Ilhwan Kim , Namhoon Kim , Jaewon Lee

Statistical n-gram language models are widely used for context-biasing tasks in Automatic Speech Recognition (ASR). However, existing implementations lack computational efficiency due to poor parallelization, making context-biasing less…

Audio and Speech Processing · Electrical Eng. & Systems 2025-05-30 Vladimir Bataev , Andrei Andrusenko , Lilit Grigoryan , Aleksandr Laptev , Vitaly Lavrukhin , Boris Ginsburg
‹ Prev 1 2 3 10 Next ›