A fast segmental Viterbi algorithm for large vocabulary recognition

Laface, Pietro; Vair, Claudio; Fissore, L.

doi:10.1109/icassp.1995.479659

Cited by 10 publications

(5 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have since discovered how to achieve the same result by an inexpensive search of a graph imposes diphone constraints on phoneme strings. The problem of locating segment boundaries in the course of the search has also been tackled by other researchers and some interesting approaches have been developed which have the advantage of not requiring a prior backward pass (Paul, 1995;Laface et al, 1995). However at the time when we first began designing our search algorithms for continuous speech the natural choice was that the first pass through the data should be in the reverse-time direction.…”

Section: Segmentationmentioning

confidence: 98%

Bi-directional graph search strategies for speech recognition

Zhi-shun¹,

Labute²,

Barszcz³

et al. 1996

Computer Speech & Language

View full text Add to dashboard Cite

Section: Segmentationmentioning

confidence: 98%

Bi-directional graph search strategies for speech recognition

Zhi-shun¹,

Labute²,

Barszcz³

et al. 1996

Computer Speech & Language

View full text Add to dashboard Cite

“…

…”

mentioning

confidence: 99%

Segmental search for continuous speech recognition

Laface¹,

Fissore²,

Maro³

et al. 1996

4th International Conference on Spoken Language Processing (ICSLP 1996)

View full text Add to dashboard Cite

The paper illustrates a search strategy for continuous speech recognition based on the recently developed Fast Segmental Viterbi Algorithm (FSVA) [5], a new search strategy particularly eective for very large vocabulary word recognition. The FSVA search has been extended to deal with continuous speech using a network that merges a general lexical tree and a set of bigram subtrees generated on demand during the search. Results are given for a 751-words speaker independent spontaneous speech recognizer of a railway timetable inquiry application, managed by a dialog system. Preliminary tests have been performed on the Wall Street

show abstract

“…The use of over-segmentation at the sub-word level is described into more detail in the respective sections devoted to specialized lexicon decoders. An example of this kind of techniques can be found in the literature: in [Laface et al 1995; Section 3] the tree lexicon arcs are only activated when the corresponding phonetic boundary is likely to be located at this point. A novel different type of segmentation information, known as "sure frontier" and described in Section 3.1.4, can be used to prune all hypotheses excepting some sub-word transitions.…”

Section: External Over-segmentationmentioning

confidence: 99%

Contributions to the joint segmentation and classification of sequences (My two cents on decoding and handwriting recognition)

Boquera¹

View full text Add to dashboard Cite

To my family, past, present and future, very specially to my parents and to my wife Manuela for their unconditional love and support. v 65 3.1.8 Prediction/Forecasting 65 3.1.9 Translation 65 3.1.10 Alignment 66 3.1.11 KWS, indexing, querying by example 69 3.1.12 Unsupervised term discovery 72 3.1.13 Filtering/Denoising and Smoothing 73 3.1.14 Summarization 73 3.1.15 Joint Segmentation and Classification 74 3.2 Some extensions 80 3.2.1 Several input sequences 80 3.2.2 Interactive systems 82 xv xvi Contents 3.3 Limitations, how to face them, new proposal 87 3.4 Questionnaire when faced with a new problem 91 3.5 Analysis and evaluation measures 93 3.5.1 Quality assessment 96 3.5.2 Performance 99 3.5.3 Interaction 100 3.5.4 Other measures 102 3.6 Summary and some conclusions 102 105 4.1 Some preliminary ML concepts 106 4.1.1 (Probabilistic) graphical models 115 4.2 Two stage generative model 130 4.2.1 Hierarchy for the second stage 133 4.2.2 Limitations, extensions and generalizations 137 4.3 Classical problems of two stage generative models 141 4.3.1 Probability of observation 142 4.3.2 Decoding 144 4.3.3 Model estimation 145 4.4 Some alternative models 146 4.4.1 Relationship with Dynamic Graphical Models 146 4.4.2 Fixed dimension feature segments 150 4.4.3 Estimation of frame-wise segment posteriors 155 4.4.4 Graph transformer networks 160 4.4.5 Some non-probabilistic frameworks 163 4.5 Summary and some conclusions 165 , , , 167 5.1 Introduction 167 5.2 Recognition, parsing, decoding 170 5.3 Weighted languages and semirings 172 5.4 Some formalisms 177 5.4.1 Formal/generative grammars 177 5.4.2 Finite state automata and transducers 184 5.4.3 Recurrent transition networks 187 5.5 Deriving the composition of a regular and a CF model 194 5.5.1 State-pair transducer composition 195 5.5.2 Extension to null-transitions 200 5.5.3 Extension to model reference transitions 209 5.5.4 Transformation to homogeneous epsilon form 220 5.6 Review of parsing approaches, decoders and algorithms 225 5.7 From composition to recognition/decoding 232 5.7.1 Acyclic inputs 233 5.7.2 Semiring specific optimizations 235 5.8 Summary and some conclusions 235 239 6.1 Probabilistic decompositions 242 6.1.1 Chain rule, clustering histories 243 6.1.2 Whole sentence LMs 244 6.1.3 Combining spans of the sequence 245 6

show abstract

A fast segmental Viterbi algorithm for large vocabulary recognition

Cited by 10 publications

References 4 publications

Bi-directional graph search strategies for speech recognition

Bi-directional graph search strategies for speech recognition

Segmental search for continuous speech recognition

Contributions to the joint segmentation and classification of sequences (My two cents on decoding and handwriting recognition)

Contact Info

Product

Resources

About