Optimization of Weighted Finite State Transducer for Speech Recognition

Aubert, Louis-Marie; Woods, Roger; Fischaber, Scott; Veitch, Richard

doi:10.1109/tc.2013.51

Cited by 3 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mel Frequency Cepstral Coefficients (MFCCs) are a feature widely used in automatic speech and speaker recognition. They were introduced by Davis and Mermelstein in the 1980's, and have been state-ofthe-art ever since [5]. This paper provides an overview of speech recognition system and the review of techniques available at various stages of speech recognition in Indian Languages.…”

Section: Introductionmentioning

confidence: 99%

A Review on Automatic Speech Recognition System in Indian Regional Languages

Siddharth¹,

Prashantkumar²,

Sunil³

2018

IJCA

View full text Add to dashboard Cite

Speech Recognition is the system whose allows a user to use their voice in the form of input data. It may be used to command text to the computer and give order to the computer system. Speech technologies are commonly used available for an unlimited but most important range of tasks. Older speech recognition application needs to identify each single world by the different phases. This process allow to the machine to conclude where one word begins and the next word stops. This type of speech recognition application are still used to direct to the computer's system. And operate applications like web browser and spread sheets. New speech recognition system allow a user to order text fluently into the system. The system that allow continuous speech are generally designed to recognize text and format it, rather than controlling the computer system itself.in This research paper studied various types of techniques which is mostly used in automatic speech recognition.

show abstract

Section: Introductionmentioning

confidence: 99%

A Review on Automatic Speech Recognition System in Indian Regional Languages

Siddharth¹,

Prashantkumar²,

Sunil³

2018

IJCA

View full text Add to dashboard Cite

show abstract

“…We are not aware of any actual decoder using these ideas and have not seen that described in the previous literature. Indeed, quite recent works such as [Kisun et al 2009] and [Aubert et al 2013;Section 4.1] rely on the recursive traversal, which is the inefficient version described before.…”

Section: Null Transitionsmentioning

confidence: 99%

“…Let us describe how to easily achieve that. Unfortunately, even recent 34 papers such as [Aubert et al 2013;Fig. 7] describe beam and histogram pruning techniques which only apply these techniques to discard hypotheses when processing the next frame.…”

Section: Histogram Pruningmentioning

confidence: 99%

“…Relating our implementation, we have tried both histogram pruning and heaps, although heaps has only been used to store scores and to provide the a pruning threshold. There exists some techniques based on modifying the pruning threshold in order to approximate histogram pruning without explicitly storing information on the best maxHyps scores [Aubert et al 2013].…”

Section: Histogram Pruningmentioning

confidence: 99%

See 1 more Smart Citation

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