K-TLSS(S) language models for speech recognition

Bordel, Germán; Varona, Amparo; Torres, M. Inés

doi:10.1109/icassp.1997.596057

Cited by 8 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To obtain the recognition rates, a test set of 600 utterances was used. The acoustic models of the system were fixed, and the language modelling part was implemented by means of K-TLSS(S) (KTestable Language in the Strict Sense, smoothed) which are a kind of Variable N-grams [7]. 8262 sentences were used for training and 1147 for test.…”

Section: Resultsmentioning

confidence: 99%

Using non-word lexical units in automatic speech understanding

Peñagarikano

Bordel

Varona

et al. 1999

1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258)

Self Cite

View full text Add to dashboard Cite

If the objective of a Continuous Automatic Speech Understanding system is not a speech-to-text translation, words are not strictly needed, and then the use of alternative lexical units (LUs) will bring us a new degree of freedom to improve the system performance. Consequently, we experimentally explore some methods to automatically extract a set of LUs from a Spanish training corpus and verify that the system can be improved in two ways: reducing the computational costs and increasing the recognition rates. Moreover, preliminary results point out that, even if the system target is a speech-to-text translation, using non-word units and post-processing the output to produce the corresponding word chain outperforms the word based system. *

show abstract

Section: Resultsmentioning

confidence: 99%

Using non-word lexical units in automatic speech understanding

Peñagarikano

Bordel

Varona

et al. 1999

1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The acoustic models were fixed and the language modelling part has been implemented by means of K-TLSS(S) (K-Testable Language in the Strict Sense, Smoothed) which are a kind of Variable N-grams [6]. 8.262 sentences have been used for training.…”

Section: Lexical Unit Based Recognition Systemmentioning

confidence: 99%

Speech-to-text translation by a non-word lexical unit based system

Peñagarikano

Bordel²

ISSPA '99. Proceedings of the Fifth International Symposium on Signal Processing and Its Applications (IEEE Cat. No.99EX359)

Self Cite

View full text Add to dashboard Cite

Speech understanding applications where a word based output of the uttered sentence is not needed, can benefit from the use of alternative lexical units. Experimental results from these systems show that the use of non word lexical units bring us a new degree of freedom in order to improve the system performance (better recognition rate and lower size can be obtained in comparison to word based models). However, if the aim of the system is a speechto-text translation, a post-processing stage must be included in order to convert the non-word sequences into word sentences. In this paper a technique to perform this conversion as well as an experimental test carried out over a task oriented Spanish corpus are reported. As a conclusion, we see that the whole speech-to-text system neatly outperforms the word-constrained baseline system.

show abstract

“…Let us remember that n-grams are essentially a family of regular languages. 45 Indeed, several authors have proposed to use WFSTs to represent n-gram models [Riccardi et al 1995;Bordel et al 1997;Llorens Piñana 2000;Vidal et al 2005b], an issue to be discussed in Section 9.2.…”

Section: Weighted Finite Automatamentioning

confidence: 99%

“…Relating the use of this formalism to represent LMs, it is widely known that n-grams are a particular class of regular languages . Several authors have proposed to use WFSTs to represent n-gram models [Riccardi et al 1995;Bordel et al 1997;Llorens Piñana 2000;Vidal et al 2005b]. But note that other types of WFST-based LMs exists besides n-grams.…”

Section: Automaton Interfacementioning

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

K-TLSS(S) language models for speech recognition

Cited by 8 publications

References 12 publications

Using non-word lexical units in automatic speech understanding

Using non-word lexical units in automatic speech understanding

Speech-to-text translation by a non-word lexical unit based system

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

Contact Info

Product

Resources

About