shu-icslp

shu-icslp - EM TRAINING OF FINITE-STATE TRANSDUCERS AND ITS...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: EM TRAINING OF FINITE-STATE TRANSDUCERS AND ITS APPLICATION TO PRONUNCIATION MODELING Han Shu and I. Lee Hetherington Spoken Language Systems Group Laboratory for Computer Science Massachusetts Institute of Technology Cambridge, Massachusetts 02139 USA { hshu,ilh } @sls.lcs.mit.edu ABSTRACT Recently, finite-state transducers (FSTs) have been shown to be useful for a number of applications in speech and lan- guage processing. FST operations such as composition, de- terminization, and minimization make manipulating FSTs very simple. In this paper, we present a method to learn weights for arbitrary FSTs using the EM algorithm. We show that this FST EM algorithm is able to learn pronun- ciation weights that improve the word error rate for a spon- taneous speech recognition task. 1. INTRODUCTION Recently, finite-state transducers (FSTs) have been shown to be useful for a number of applications in speech and language processing [1]. For example, the summit segment- based speech recognizer successfully utilizes FSTs to specify various constraints [2]. FST operations such as composi- tion, determinization, and minimization make manipulat- ing FSTs very simple. In this paper, we present a method to learn weights for arbitrary FSTs using the EM algorithm [3]. Our method is similar to that of [4]; however we do not explicitly make use of the “expectation semiring.” To test the FST EM algorithm, we apply the algorithm to the problem of learning pronunciation weights. With phonological rules and multiple phonemic pronunciations, the pronunciation graph for spontaneous speech can have high branching factors. Pronunciation weighting has been shown to be beneficial for segment-based speech recogni- tion [5]. In [5] within-word pronunciation weights were ML estimated from training examples. In this paper, we experi- ment with learning various pronunciation weights on phono- logical rules and phonemic pronunciations via the proposed FST EM algorithm. 2. PROBABILISTIC INTERPRETATION OF FSTS A weighted FST, T , assigns a weight, or score, to each com- plete path through it, where a path corresponds to a partic- This research was supported by DARPA under contract N66001-99-1-8904 monitored through Naval Command, Control and Ocean Surveillance Center. ular input and output label sequence ( x, y ). The interpre- tation of the weights depends on how they are manipulated algebraically, and the algebraic structure is a semiring. 2.1. Weight Semirings A semiring ( , ⊕ , ⊗ , , 1) defines the set containing the weights, the operators ⊕ and ⊗ , with the identity elements and 1 such that for all a, b, c ∈ , a ⊕ 0 = a , ⊕ a = a , a ⊗ 1 = a , 1 ⊗ a = a , a ⊗ 0 = 0, ⊗ a = 0, ( a ⊕ b ) ⊗ c = ( a ⊗ c ) ⊕ ( b ⊗ c ), and a ⊗ ( b ⊕ c ) = ( a ⊗ b ) ⊕ ( a ⊗ c ) [1]. When manipulating weighted transducers, the ⊗ and ⊕ operators are used to combine weights in series and parallel, respectively....
View Full Document

This note was uploaded on 05/08/2010 for the course CS 6.345 taught by Professor Glass during the Spring '10 term at MIT.

Page1 / 4

shu-icslp - EM TRAINING OF FINITE-STATE TRANSDUCERS AND ITS...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online