Efficient determinization of tagged word lattices using categorial and lexicographic semirings

Shafran, Izhak; Sproat, Richard; Yarmohammadi, Mahsa; Roark, Brian

doi:10.1109/asru.2011.6163945

Cited by 6 publications

(6 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One, due to Povey et al (2012), is described in Section 3.1. Our own work, also previously reported in Shafran et al (2011), is presented in Sections 3.2 and 3.3. In Section 3.4 we compare the approaches for efficiency.…”

Section: Tagging Determinization On Latticesmentioning

confidence: 88%

Applications of Lexicographic Semirings to Problems in Speech and Language Processing

Sproat

Yarmohammadi

Shafran

et al. 2014

Computational Linguistics

Self Cite

View full text Add to dashboard Cite

This article explores lexicographic semirings and their application to problems in speech and language processing. Specifically, we present two instantiations of binary lexicographic semirings, one involving a pair of tropical weights, and the other a tropical weight paired with a novel string semiring we term the categorial semiring. The first of these is used to yield an exact encoding of backoff models with epsilon transitions. This lexicographic language model semiring allows for off-line optimization of exact models represented as large weighted finite-state transducers in contrast to implicit (on-line) failure transition representations. We present empirical results demonstrating that, even in simple intersection scenarios amenable to the use of failure transitions, the use of the more powerful lexicographic semiring is competitive in terms of time of intersection. The second of these lexicographic semirings is applied to the problem of extracting, from a lattice of word sequences tagged for part of speech, only the single best-scoring part of speech tagging for each word sequence. We do this by incorporating the tags as a categorial weight in the second component of a Tropical, Categorial lexicographic semiring, determinizing the resulting word lattice acceptor in that semiring, and then mapping the tags back as output labels of the word lattice transducer. We compare our approach to a competing method due to Povey et al. (2012).

show abstract

Section: Tagging Determinization On Latticesmentioning

confidence: 88%

Applications of Lexicographic Semirings to Problems in Speech and Language Processing

Sproat

Yarmohammadi

Shafran

et al. 2014

Computational Linguistics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Since there are multiple labels and weights on the arc, in order to do WFST computations, we need to extend the traditional single-weight (scalar) semiring to a vector semiring. We build on Shafran et al's idea [2] of the lexicographic semiring which carries multiple weights, but our weights correspond to scores from multiple acoustic models.…”

Section: Methodsmentioning

confidence: 99%

“…In recent years, different types of semirings have been proposed for various purposes. For example, the lexicographic semiring by Shafran et al [2] is used for determinizing tagged word lattices. Also, van Dalen et al [3] report the use of expectation semiring to efficiently extract features.…”

Section: Introductionmentioning

confidence: 99%

A WFST Framework for Single-Pass Multi-Stream Decoding

Fosler‐Lussier

2016

Interspeech 2016

View full text Add to dashboard Cite

Combining disparate automatic speech recognition systems has long been an important strategy to improve recognition accuracy. Typically, each system requires a separate decoder; final results are derived by combining hypotheses from multiple lattices, necessitating multiple passes of decoding. We propose a novel Weighted Finite State Transducer (WFST) framework for integrating disparate systems. Our framework is different from the current popular system combination techniques in that the combination is done in one-pass decoding and allows the flexibility to combine systems at different levels of the decoding pipeline. Initial experiments with the framework achieved comparable performance as MBR-based combination which is reported to outperform ROVER and Confusion Network Combination (CNC). In this paper, we describe our methodology and present pilot study results for combining systems that use different sets of acoustic models, 1) gender-dependent GMM models, 2) MFCC and PLP features with GMM models, 3) MFCC, PLP and Filter Bank features with DNN models, and 4) SNR-specific DNN acoustic models. For each experiment, we also compared the computation time of the combined systems with their corresponding baseline systems. Our results show encouraging benefits of using the proposed framework to improve recognition performance while reducing computation time.

show abstract

“…Since submitting this paper, we have become aware of [10], which solves the exact same problem for a different purpose. They use a semiring which is more complicated than ours (the string part of the semiring becomes a structured object with parentheses).…”

Section: Details Of Our Determinization Algorithmmentioning

confidence: 99%

Generating exact lattices in the WFST framework

Povey

Hannemann

Boulianne

et al. 2012

2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

119

110

View full text Add to dashboard Cite

We describe a lattice generation method that is exact, i.e. it satisfies all the natural properties we would want from a lattice of alternative transcriptions of an utterance. This method does not introduce substantial overhead above one-best decoding. Our method is most directly applicable when using WFST decoders where the WFST is "fully expanded", i.e. where the arcs correspond to HMM transitions. It outputs lattices that include HMM-state-level alignments as well as word labels. The general idea is to create a state-level lattice during decoding, and to do a special form of determinization that retains only the best-scoring path for each word sequence. This special determinization algorithm is a solution to the following problem: Given a WFST A, compute a WFST B that, for each input-symbolsequence of A, contains just the lowest-cost path through A.

show abstract

Efficient determinization of tagged word lattices using categorial and lexicographic semirings

Cited by 6 publications

References 6 publications

Applications of Lexicographic Semirings to Problems in Speech and Language Processing

Applications of Lexicographic Semirings to Problems in Speech and Language Processing

A WFST Framework for Single-Pass Multi-Stream Decoding

Generating exact lattices in the WFST framework

Contact Info

Product

Resources

About