paper-with-me

홈 › Papers

Parallel Composition of Weighted Finite-State Transducers

2021-10-06 · Shubho Sengupta, Vineel Pratap, Awni Hannun

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 more computationally expensive operations. Due to the heterogeneous structure of FSTs, parallel algorithms for composition are suboptimal in efficiency, generality, or both. We propose an algorithm for parallel composition and implement it on graphics processing units. We benchmark our parallel algorithm on the composition of random graphs and the composition of graphs commonly used in speech recognition. The parallel composition scales better with the size of the input graphs and for large graphs can be as much as 10 to 30 times faster than a sequential CPU algorithm.

📄 PDF Abstract BibTeX arXiv:2110.02848

Code (0)

등록된 구현이 없습니다.

Tasks

CPUspeech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

Composing Finite State Transducers on GPUs

2018-05-16 · ACL 2018 7 · Arturo Argueta, David Chiang

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 accelera…

CPUGPUPart-Of-Speech Taggingspeech-recognition+1

Decoding with Finite-State Transducers on GPUs

2017-01-11 · EACL 2017 4 · Arturo Argueta, David Chiang

Weighted finite automata and transducers (including hidden Markov models and conditional random fields) are widely used in natural language processing (NLP) to perform tasks such as morphological analysis, part-of-speech…

ChunkingGPUMorphological Analysisnamed-entity-recognition+5

A Transaction Represented with Weighted Finite-State Transducers

2023-02-01 · J. Nathaniel Holmes, Homayoon Beigi

Not all contracts are good, but all good contracts can be expressed as a finite-state transition system ("State-Transition Contracts"). Contracts that can be represented as State-Transition Contracts discretize fat-taile…

Differentiable Weighted Finite-State Transducers

2020-10-02 · Awni Hannun, Vineel Pratap, Jacob Kahn, Wei-Ning Hsu

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, thi…

Handwriting Recognitionspeech-recognitionSpeech Recognition

Transliterated Mobile Keyboard Input via Weighted Finite-State Transducers

2017-09-01 · WS 2017 9 · Lars Hellsten, Brian Roark, Prasoon Goyal, Cyril Allauzen 외
Language ModelingLanguage ModellingOptical Character Recognition (OCR)Speech Recognition+1