A new class of fenonic Markov word models for large vocabulary continuous speech recognition

Bahl, Lalit R.; Bellegarda, Jerome R.; deSouza, P.V.; Gopalakrishnan, P.S.; Nahamoo, D.; Picheny, Michael

doi:10.1109/icassp.1991.150306

Cited by 7 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Examples for Gaussian mixture sharing are the semi-continuous HMMs as proposed by Huang and Jack (1989) or in a more general framework, the tied mixture models presented by Bellegarda and Nahamoo (1990). Another data-driven parameter tying scheme is the use of fenones as phone model building blocks (see Bahl et al, 1991) which has a more direct relationship to standard pronunciation strings. More recently Luo and Jelinek (1999) have introduced a method for the soft-tying of states, which was used by Saraçlar et al (2000) to model pronunciation variability in spontaneous speech.…”

Section: Parameter Tyingmentioning

confidence: 98%

Implicit modelling of pronunciation variation in automatic speech recognition

Hain

2005

Speech Communication

View full text Add to dashboard Cite

Section: Parameter Tyingmentioning

confidence: 98%

Implicit modelling of pronunciation variation in automatic speech recognition

Hain

2005

Speech Communication

View full text Add to dashboard Cite

“…Speech units, according to the derivation rule, are obtained either by a linguistic criterion or by an automatic clustering technique (Černocký, 2002). Examples of speech units according to the automatic clustering technique are fenones (Bahl et al, 1993), senones (Hwang and Huang, 1992), and multones (Bahl et al, 1996). Speech units according to the linguistic criterion are common to all the languages: phonemes, diphthongs, syllables.…”

Section: Related Workmentioning

confidence: 99%

Framework for Choosing a Set of Syllables and Phonemes for Lithuanian Speech Recognition

Laurinčiukaitė¹,

Lipeika²

2007

Informatica

View full text Add to dashboard Cite

This paper describes a framework for making up a set of syllables and phonemes that subsequently is used in the creation of acoustic models for continuous speech recognition of Lithuanian. The target is to discover a set of syllables and phonemes that is of utmost importance in speech recognition. This framework includes operations with lexicon, and transcriptions of records. To facilitate this work, additional programs have been developed that perform word syllabification, lexicon adjustment, etc. Series of experiments were done in order to establish the framework and model syllable-and phoneme-based speech recognition. Dominance of a syllable in lexicon has improved speech recognition results and encouraged us to move away from a strict definition of syllable, i.e., a syllable becomes a simple sub-word unit derived from a syllable. Two sets of syllables and phonemes and two types of lexicons have been developed and tested. The best recognition accuracy achieved 56.67% ±0.33. The speech recognition system is based on Hidden Markov Models (HMM). The continuous speech corpus LRN0 was used for the speech recognition experiments.

show abstract

“…Sub-word units associated to phonemes and syllables are based on concepts given by phoneticians, but it is also possible to envisage a set of units determined automatically from a corpus of speech utterances, as is the case of fenones and multones (a set of fenones in parallel) which are obtained by means of clustering and vector quantization [Bahl et al 1991]. A similar automatic clustering of HMM states with loops leads to a representation known as senones [Hwang and Huang 1992].…”

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

A new class of fenonic Markov word models for large vocabulary continuous speech recognition

Cited by 7 publications

References 8 publications

Implicit modelling of pronunciation variation in automatic speech recognition

Implicit modelling of pronunciation variation in automatic speech recognition

Framework for Choosing a Set of Syllables and Phonemes for Lithuanian Speech Recognition

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

Contact Info

Product

Resources

About