Acoustic-phonetic modeling for flexible vocabulary speech recognition

Fissore, L.; Ravera, Franco; Laface, Pietro

doi:10.21437/eurospeech.1995-183

Cited by 23 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We refer to the sub-word used for the acoustic modeling as Stationary-Transition Units (STU) [3]. The set of these units include the stationary parts of the context independent phonemes (less affected by the phonetic context) and all the admissible transitions between them.…”

Section: Speech Modeling With Hybrid Hmm-nnmentioning

confidence: 99%

Synergy of spectral and perceptual features in multi-source connectionist speech recognition

Gemello¹,

Moisa²,

Laface³

2000

6th International Conference on Spoken Language Processing (ICSLP 2000)

Self Cite

View full text Add to dashboard Cite

The combined use of different set of features extracted from the speech signal with different processing algorithms is a promising approach to improve speech recognition performances.Artificial Neural Networks are well suited to this task since they are able to use directly multiple heterogeneous input features to estimate a near optimal combination of them for classification, without being constrained by a priori assumptions on the stochastic independence of the input sources.This work shows how we have taken advantage of these characteristics of Neural Networks to improve the recognition accuracy of our systems. In particular, three set of input features have been considered as sources in this work: Mel based Cepstral Coefficients derived from the FFT spectrum, RASTA-PLP Cepstral Coefficients, and a set of features that describe the dynamics of the FFT power spectrum along the frequency dimension, instead of the usual time dimension.The experimental results confirm the usefulness of the proposed approach of feature integration that leads to a significant error reduction both on isolated and continuous speech recognition tasks on a large telephone speech test set.

show abstract

Section: Speech Modeling With Hybrid Hmm-nnmentioning

confidence: 99%

Synergy of spectral and perceptual features in multi-source connectionist speech recognition

Gemello¹,

Moisa²,

Laface³

2000

6th International Conference on Spoken Language Processing (ICSLP 2000)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Although the dependence of both side contexts is not taken into account, the number of models is reduced with respect to triphones. Stationary-Transitional Units [Fissore et al 1996;Gemello et al 1997] are based on similar ideas. Some researchers distinguish different time scales in speech: subsegmental features can be analyzed in a range between 25 and 80ms, whereas the phonetic information is integrated at syllabic timescales (150-300ms).…”

Section: Sub-word Unitsmentioning

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

Continuous Speech Recognition with Neural Networks: An Application to Railway Timetables Enquires

Albesano

Mana

Gemello

1999

Speech Processing, Recognition and Artificial Neural Networks

View full text Add to dashboard Cite

Acoustic-phonetic modeling for flexible vocabulary speech recognition

Cited by 23 publications

References 0 publications

Synergy of spectral and perceptual features in multi-source connectionist speech recognition

Synergy of spectral and perceptual features in multi-source connectionist speech recognition

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

Continuous Speech Recognition with Neural Networks: An Application to Railway Timetables Enquires

Contact Info

Product

Resources

About