Filters








32 Hits in 5.9 sec

Diphones-fr: A French database of diphone positional frequency

Boris New, Elsa Spinelli
2012 Behavior Research Methods  
We also provide intra-and intersyllable diphone frequencies, as well as interword diphone frequencies.  ...  More specifically, we provide frequencies for word-initial, word-internal, and word-final diphones of all words extracted from a subtitle corpus of 50 million words that come from movie and TV series dialogue  ...  They assessed whether the model could recover word boundaries based on the identity of the surrounding diphone.  ... 
doi:10.3758/s13428-012-0285-y pmid:23239073 fatcat:ov6c2stntbcjzo4wm2xsxlktzi

Lexicographers' Dreams in the Electronic-Dictionary Age

G.-M. de Schryver
2003 International Journal of Lexicography  
sorting and scrutinising one hundred and twenty dreams found throughout the literature (section six).  ...  Section seven concludes with some observations on the way ahead.  ...  That model indicated the way in which learners utilised the ED, and based on that the aim was to orient, evaluate and advise the learner.  ... 
doi:10.1093/ijl/16.2.143 fatcat:xxtnzs6pqzervkekexz5niri4u

Statistical Analysis of Mandarin Acoustic Units and Automatic Extraction of Phonetically Rich Sentences Based Upon a very Large Chinese Text Corpus

Hsin-Min Wang
1998 International Journal of Computational Linguistics and Chinese Language Processing  
This paper first presents statistical analysis of various Mandarin acoustic units based upon a very large Chinese text corpus collected from daily newspapers and then presents an algorithm to automatically  ...  However, it is believed that an adequate speech database for training acoustic models and evaluating performance is certainly critical for successful deployment of such systems in realistic operating environments  ...  Yu-hsueh Chou and Mr. Yuan-cheng Chang for their contributions in programming. Special thanks are due to Prof. Lin-shan Lee for many helpful comments.  ... 
dblp:journals/ijclclp/Wang98 fatcat:ujtunjbwcneqxetbaxlbbooezy

Prosodic Boundary Prediction for Greek Speech Synthesis

Panagiotis Zervas
2013 Journal of Computer Sciences and Applications  
Resulted datasets were applied to C4.5 decision tree, one-neighbour instance based learner and Bayesian learning methods.  ...  Feature contribution was evaluated and ranked with the application of information gain ranking and correlation -based feature selection filtering methods.  ...  In the past, such prediction was conducted using simple phrasing algorithms [6] based on orthographic indicators, keywords or part-of-speech (POS) spotting and simple timing in formation.  ... 
doi:10.12691/jcsa-1-4-2 fatcat:tyaege3sm5bcxl65azkxqll7be

Towards increasing speech recognition error rates

Hervé Bourlard, Hynek Hermansky, Nelson Morgan
1996 Speech Communication  
Issues that will be addressed in this paper include: discrimination between rival utterance models, the role of prior information in speech recognition, merging the language and acoustic models, feature  ...  In the field of Automatic Speech Recognition ASR research, it is conventional to pursue those approaches that reduce the word error rate.  ...  features while minimizing the intra-class variance and maximizing the inter-class variance.  ... 
doi:10.1016/0167-6393(96)00003-9 fatcat:zagl4mxdljcvrl2s6bie3inwhu

Durational Differences of Word-Final /s/ Emerge From the Lexicon: Modelling Morpho-Phonetic Effects in Pseudowords With Linear Discriminative Learning

Dominic Schmitz, Ingo Plag, Dinah Baer-Henney, Simon David Stein
2021 Frontiers in Psychology  
That is, duration of word-final /s/ in pseudowords can be predicted based on their relations to the lexicon.  ...  Following a recent approach, we implemented a linear discriminative learning network trained on real word data in order to predict the duration of word-final non-morphemic and plural /s/ in pseudowords  ...  In the NDL network, all words and their diphones within a five word window centred on the target word that contained the S served as cues, and were associated with the morphological functions, which served  ... 
doi:10.3389/fpsyg.2021.680889 fatcat:rimefygt7vahjlacazytkkqnk4

Computational intelligence in processing of speech acoustics: a survey

Amitoj Singh, Navkiran Kaur, Vinay Kukreja, Virender Kadyan, Munish Kumar
2022 Complex & Intelligent Systems  
This paper presents a comprehensive survey on the speech recognition techniques for non-Indian and Indian languages, and compiled some of the computational models used for processing speech acoustics.  ...  When compared with non-Indian languages, the research on speech recognition of Indian languages (except Hindi) has not achieved the expected milestone yet.  ...  In: INTER-SPEECH'2006, pp 441-446 70.  ... 
doi:10.1007/s40747-022-00665-1 fatcat:6pu2xccbq5as7bn2y2tav2fdwa

Analyzing and Improving Statistical Language Models for Speech Recognition [article]

Joerg P. Ueberla
1994 arXiv   pre-print
It can incorporate linguistic knowledge even if it extends over many words and this is not feasible in a traditional N-pos model.  ...  Moreover, one of the identified weaknesses has prompted the development of our generalized N-pos language model, which is also outlined in this thesis.  ...  For example, there is intra-speaker variability due to the speaking mode (singing, shouting, with a cold, under stress, speaking rate, etc.), inter-speaker variability (sex, age etc.) and variability due  ... 
arXiv:cmp-lg/9406027v1 fatcat:f2ufszn3xrezlk47eframprwyu

Why not model spoken word recognition instead of phoneme monitoring?

Jean Vroomen, Beatrice de Gelder
2000 Behavioral and Brain Sciences  
Because phonemic decisions are based on the merging of prelexical and lexical information, Merge correctly predicts lexical involvement in phonemic decisions in both words and nonwords.  ...  Feedback is accordingly unnecessary and spoken word recognition is modular. To defend this thesis, we analyse lexical involvement in phonemic decision making.  ...  The major empirical methods in comprehension research have been metalinguistic: phoneme decision, lexical decision, word spotting, and so on.  ... 
doi:10.1017/s0140525x00493246 fatcat:kvpp3ouce5ecvkllnlnl6r427a

Merging information in speech recognition: Feedback is never necessary

Dennis Norris, James M. McQueen, Cutler
2000 Behavioral and Brain Sciences  
Because phonemic decisions are based on the merging of prelexical and lexical information, Merge correctly predicts lexical involvement in phonemic decisions in both words and nonwords.  ...  The logic of the process requires information to flow in one direction: from sounds to words.  ...  The major empirical methods in comprehension research have been metalinguistic: phoneme decision, lexical decision, word spotting, and so on.  ... 
doi:10.1017/s0140525x00003241 fatcat:fxfjq33eevei7fmthzn7hv2i3a

A coupled bispectral, temporal and spatial coherence function of the pressure field, scattered from a moving sea surface

Christian Bjerrum‐Niese, Leif Bjo/rno/
1995 Journal of the Acoustical Society of America  
Working group chairs will report on their preparation of standards on methods of measurement and testing, and terminology, in physical acoustics, electro-acoustics, sonics, ultrasonics, and underwater  ...  Standards Committee S1 on Acoustics.  ...  This paper presents results and analysis of inter-and intra-tile coupling mechanisms, including particularly an evaluation of the role of the backing structure. 3:15 2pEA9.  ... 
doi:10.1121/1.414267 fatcat:gtdrkztuvfbova3a4rdj2f7umu

Acoustic source identification in an enclosed space using the inverse phased beam tracing at medium frequencies

Jeong‐Guon Ih, Cheol‐Ho Jeong
2008 Journal of the Acoustical Society of America  
and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. • Users may download and print one copy of any publication from the  ...  we will remove access to the work immediately and investigate your claim.  ...  It is based on Gaussian-Mixture Models ͑GMM͒, trained for the pitch and the duration of diphones.  ... 
doi:10.1121/1.2933749 fatcat:xiro7xkminfl5o3psp2ejziawq

A binaural advantage in the subjective modulation transfer function with simple impulse responses

Eric R. Thompson, Torsten Dau
2008 Journal of the Acoustical Society of America  
It is based on Gaussian-Mixture Models ͑GMM͒, trained for the pitch and the duration of diphones.  ...  on Hot Spots.  ...  The ability of such TRA focusing system based on random reverberator to form simultaneously multiple focuses and produce focal spots of the complex shape has been demonstrated.  ... 
doi:10.1121/1.2933699 fatcat:4nc5pg4ysbhgrjcatwhr7fh77q

On determination of microphone response and other parameters by a hybrid experimental and numerical method

Salvador Barrera‐Figueroa, Finn Jacobsen, Knud Rasmussen
2008 Journal of the Acoustical Society of America  
It is based on Gaussian-Mixture Models ͑GMM͒, trained for the pitch and the duration of diphones.  ...  on Hot Spots.  ...  The ability of such TRA focusing system based on random reverberator to form simultaneously multiple focuses and produce focal spots of the complex shape has been demonstrated.  ... 
doi:10.1121/1.2933455 fatcat:gl6kkwih6rbkriigc7g6ghdlnq

The importance of bass clarity in pop and rock venues

Niels W. Adelman‐Larsen, Eric R. Thompson
2008 Journal of the Acoustical Society of America  
It is based on Gaussian-Mixture Models ͑GMM͒, trained for the pitch and the duration of diphones.  ...  on Hot Spots.  ...  The ability of such TRA focusing system based on random reverberator to form simultaneously multiple focuses and produce focal spots of the complex shape has been demonstrated.  ... 
doi:10.1121/1.2932922 fatcat:fvtlbt6x5vgelp5p67x53qtvgi
« Previous Showing results 1 — 15 out of 32 results