Parallel Composition of Weighted Finite-State Transducers
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.
Code (0)
등록된 구현이 없습니다.
Tasks
CPUspeech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
Composing Finite State Transducers on GPUs
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+1Decoding with Finite-State Transducers on GPUs
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+5A Transaction Represented with Weighted Finite-State Transducers
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
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