FLavor: a flexible architecture for LVCSR

Demuynck, Kris; Laureys, Tom; Compernolle, Dirk Van; hamme, Hugo Van

doi:10.21437/eurospeech.2003-570

Cited by 28 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some readers may also find a slight resemblance between the semidecoupled architectures of this work, the layered approach of [Demuynck et al 2003], the bottom-up proposal from [Siniscalchi et al 2013] or even the phone-to-word decoding described in [Bertoldi et al 2008]. They mainly share with our systems the fact of using a subword DAG representation at some intermediate stage: in [Demuynck et al 2003], a phone network is generated in a first stage in order to be decoded in a subsequent one. The second stage makes use of error correction edition operations during decoding as with the proposed graph _ graph _ gen extension of Section 11.2.3.…”

Section: Other Possible Extensionsmentioning

confidence: 84%

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

Section: Other Possible Extensionsmentioning

confidence: 84%

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

show abstract

Analysis of HMM Temporal Evolution for Automatic Speech Recognition and Verification

Casar

Fonollosa

2006

Text, Speech and Dialogue

View full text Add to dashboard Cite

Vietnamese Automatic Speech Recognition: The FLaVoR Approach

Demuynck

Compernolle

2006

Chinese Spoken Language Processing

View full text Add to dashboard Cite

Abstract. Automatic speech recognition for languages in SoutheastAsia, including Chinese, Thai and Vietnamese, typically models both acoustics and languages at the syllable level. This paper presents a new approach for recognizing those languages by exploiting information at the word level. The new approach, adapted from our FLaVoR architecture[1], consists of two layers. In the rst layer, a pure acoustic-phonemic search generates a dense phoneme network enriched with meta data. In the second layer, a word decoding is performed in the composition of a series of nite state transducers (FST), combining various knowledge sources across sub-lexical, word lexical and word-based language models. Experimental results on the Vietnamese Broadcast News corpus showed that our approach is both e ective and exible.

show abstract

FLavor: a flexible architecture for LVCSR

Cited by 28 publications

References 8 publications

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

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

Analysis of HMM Temporal Evolution for Automatic Speech Recognition and Verification

Vietnamese Automatic Speech Recognition: The FLaVoR Approach

Contact Info

Product

Resources

About