Speech Recognition by Composition of Weighted Finite Automata

1996/03/07 by Fernando C. N. Pereira, Pereira, Fernando C. N., Michael D. Riley +1
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #cmp-lg #cs.CL

paper · pdf · doi:10.48550/arxiv.cmp-lg/9603001

24 pages, uses psfig.sty

arxiv created 1996/03/07 · arxiv updated 2009/11/30

Abstract

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 structures used in recognition, including context-dependent units, pronunciation dictionaries, language models and lattices. Furthermore, general but efficient algorithms can used for combining information sources in actual recognizers and for optimizing their application. In particular, a single composition algorithm is used both to combine in advance information sources such as language models and dictionaries, and to combine acoustic observations and information sources dynamically during recognition.

Related

• Algorithms for Speech Recognition and Language Processing
• Weighted Automata in Text and Speech Processing
• Transformer-based language modeling and decoding for conversational speech recognition
• Continuous Speech Recognition Based on Deterministic Finite Automata Machine using Utterance and Pitch Verification
• Use of Weighted Finite State Transducers in Part of Speech Tagging