21,330 Hits in 5.6 sec

Page 784 of Linguistics and Language Behavior Abstracts: LLBA Vol. 26, Issue 2 [page]

1992 Linguistics and Language Behavior Abstracts: LLBA  
for speaker adaptation is explored with regard to the development of a speaker-independent large-vocabulary recognition system.  ...  adaptation in speech recognition, & voice conversion techniques are discussed.  ... 

MAP Based Speaker Adaptation in Very Large Vocabulary Speech Recognition of Czech

J. Nouza, P. Cerva
2004 Radioengineering  
Severalalternative versions of this method have been implemented andexperimentally verified in two areas, first in the isolated-wordrecognition (IWR) task and later also in the large vocabularycontinuous  ...  Recently, we have used the described methods in the designof two practical applications: voice dictation to a PC and automatictranscription of radio and TV news.  ...  Conclusion This paper deals with the problem of the efficient speaker adaptation for the very large vocabulary speech recognition of Czech.  ... 
doaj:305dd47570324974b0db59ef024213be fatcat:hp3efbmdcngqtmkn5nsu5c54yu

Recognition of voice commands using adaptation of foreign language speech recognizer via selection of phonetic transcriptions

Rytis Maskeliunas, Vytautas Rudzionis
2011 Open Engineering  
All of these commercial recognizers are typically targeted to widely spoken languages having large market potential; however, it may be possible to adapt available commercial recognizers for use in environments  ...  The experimental evaluation showed that it is possible to find phonetic transcriptions that will enable the recognition of Lithuanian voice commands with recognition accuracy of over 90%.  ...  The recognition accuracy of this set is then verified, using a large multi speaker corpus.  ... 
doi:10.2478/s13531-011-0017-6 fatcat:prowmhu7gfhlnlzfpszafis7jy

Page 2234 of Psychological Abstracts Vol. 79, Issue 6 [page]

1992 Psychological Abstracts  
79: 18533-18541 dent large vocabulary recognition system. Only | speaker (the reference speaker) pronounces the application vocabulary and a small vocabulary called the adaptation vocabulary.  ...  Each new speaker (NS) then merely pronounces the adaptation vocabulary.  ... 

A cross-lingual adaptation approach for rapid development of speech recognizers for learning disabled users

Marek Bohac, Michaela Kucharova, Zoraida Callejas, Jan Nouza, Petr Červa
2014 EURASIP Journal on Audio, Speech, and Music Processing  
speech in different languages for the recognition of the users' atypical voices.  ...  In this paper, we present a cross-lingual approach to adapt a general-purpose modular speech recognizer for learning disabled people.  ...  The authors want to thank the staff from the associations JABALCON and APAFA and the participants in the recordings for their contribution to make this work possible.  ... 
doi:10.1186/s13636-014-0039-0 fatcat:7ttgpriurjdztpmhd6fuldwyya

Large-vocabulary recognition

Christian Dugast
1995 Philips Journal of Research  
This implies speech recognition for large and open vocabularies, free syntax, continuous speech.  ...  Large-vocabulary continuous-speech recognition (CSR) technology is at work. As an application of the technology, we will describe a dictation system (DS).  ...  The BS can recognize continuous speech for large to very large vocabularies, but there is no speaker-independent general purpose continuous-speech recognition system on the market.  ... 
doi:10.1016/0165-5817(96)81585-3 fatcat:2ihc2prnavc3jdat54f7jdkuw4

Speech Input from Older Users in Smart Environments: Challenges and Perspectives [chapter]

Ravichander Vipperla, Maria Wolters, Kallirroi Georgila, Steve Renals
2009 Lecture Notes in Computer Science  
Further research is needed into intelligent adaptation techniques that will allow existing large, robust systems to be adapted with relatively small amounts of in-domain, age appropriate data.  ...  In addition, older users need to be supported with adequate strategies for handling speech recognition errors. 1 National Statistics: Morbidity: Arthritis is more common in women.  ...  We conclude that innovative strategies are required for adapting existing speech recognition systems to older voices; in particular to achieve high accuracy, speech recognition systems not only need to  ... 
doi:10.1007/978-3-642-02710-9_14 fatcat:fvxl4qdhhjgg7j424uj2jhbarq

Page 1639 of Linguistics and Language Behavior Abstracts: LLBA Vol. 26, Issue 3 [page]

1992 Linguistics and Language Behavior Abstracts: LLBA  
, conjunctive postposition classification proposal; 9206752 large vocabulary speech recognition, pattern-recognition-based ap- proach, acoustic modeling techniques; 9207387 linguistic recognition system  ...  recognition/memory processes/parameters; experiments; 9205053 Voicing Arabic stops, voicing distinction, temporal acoustic cues, voice onset/ sound durations; experiments; Ghamidi dialect speakers, Saudi  ... 

The annual "arrival" of speech recognition

A.E. Cawkell
1990 Information Services and Use  
Editorial The annual "arrival" of speech recognition 133 0167-5265/90/$03.50 © 1990 -Elsevier Science Publishers B.Y.  ...  The vocabulary is limited to six isolated control words and ten digits". "We have demonstrated that large-vocabulary speaker-independent continuous speech recognition is feasible".  ...  "A voice activated 'typewriter' that can recognise 30,000 words and adapts itself to individual speakers has been unveiled...  ... 
doi:10.3233/isu-1990-10301 fatcat:pbxyhq3j5rezvfvxfdfffpneeu

Detailed author index

2009 2009 IEEE Workshop on Automatic Speech Recognition & Understanding  
Weighted Finite-State Transducers 333 Vietnamese Large Vocabulary Continuous Speech Recognition 529 Speaker De-Identification via Voice Transformation Schuppler, Barbara 70 Using Temporal Information  ...  in Ensemble Speaker and Speaking Environment Modeling Mertens, Timo 562 Lexicon Adaptation for Subword Speech Recognition Mertins, Alfred 211 Generalized Cyclic Transformations in Speaker-Independent  ... 
doi:10.1109/asru.2009.5373491 fatcat:tgoktcyotncatbvo3l3cslfapa

Communication Interface for Mexican Spanish Dysarthric Speakers

Gladys Bonilla-Enriquez, Santiago-Omar Caballero-Morales
2012 Acta Universitaria  
The interface allows the user and therapist to perform tasks such as dynamic speaker adaptation, vocabulary adaptation, and text-to-speech (TTS) synthesis.  ...  In this paper we present our advances towards the development of a communication interface for dysarthric speakers whose native language is Mexican Spanish.  ...  the language) in the training speech corpus for acoustic modelling (even if only a single speaker were used as speech source); (2) the vocabulary were not large (< 1000 words); (3) the effect of statistical  ... 
doi:10.15174/au.2012.348 fatcat:3pr3wxvw3nddfngc4ueilx7hlu

Recognition of Voice Commands Using Hybrid Approach [chapter]

Vytautas Rudžionis, Kastytis Ratkevičius, Algimantas Rudžionis, Gailius Raškinis, Rytis Maskeliunas
2013 Communications in Computer and Information Science  
In this paper the novel method is proposed for the combination of several recognition methods based on the Ripper algorithm.  ...  The paper deals with hybrid approach implementation issues for the voice commands recognition.  ...  .:31V-34/13 "Hybrid recognition technology for voice interface" (INFOBALSAS) funded by Agency for Science, Innovation and Technology.  ... 
doi:10.1007/978-3-642-41947-8_21 fatcat:pa3eup2id5eqbha6hy4ppt6ufu

Development of Large Vocabulary Continuous Speech Recognition for Polish

G. Demenko, M. Szymański, R. Cecko, E. Kuśmierek, M. Lange, K. Wegner, K. Klessa, M. Owsianny
2012 Acta Physica Polonica. A  
In this study, the results of acoustic modeling used in a large vocabulary continuous speech recognition system are presented.  ...  The present large vocabulary continuous speech recognition evaluation results were obtained with Sclite assessment software.  ...  This project is supported by the Polish Ministry of Science and Higher Education (project ID: OR00006707 Integrated system of automatic speech-to-text conversion based on linguistic modelling designed in  ... 
doi:10.12693/aphyspola.121.a-86 fatcat:wjznaujp6jae3fqp2d5ffhzimy

Web Services Based Hybrid Recognizer of Lithuanian Voice Commands

V. Rudzionis, G. Raskinis, R. Maskeliunas, A. Rudzionis, K. Ratkevicius, G. Bartisiute
2014 Elektronika ir Elektrotechnika  
All these measures and approaches allowed achieve very high speaker independent voice commands recognition accuracy acceptable for the system implementation in practice.  ...  The best achieved recognition was 98.9 % for 1000 Lithuanian voice commands. The paper presents optimization issues related with the development of the system.  ...  I RECOGNITION ACCURACY OF SEVERAL VOICE COMMANDS USING ADAPTED SPANISH RECOGNIZER BEFORE AND AFTER OPTIMIZATION.  ... 
doi:10.5755/j01.eee.20.9.8713 fatcat:oshriofy7nh4pdprx62g3ftllq

A Survey on Isolated Word and Digit Recognition using Different Techniques

Pooja Prajapati, Miral Patel
2017 International Journal of Computer Applications  
Nowadays, Spoken digit recognition is one the challenging task in the field of speech recognition.  ...  Likewise, discussing different approaches, methods & comparative analysis about recent research work done in isolated digit & word recognition in various languages.  ...  Vocabulary Size Type of vocabulary No of words contain A Small vocabulary 10 Medium vocabulary 100 Large vocabulary 1000 Very large vocabulary 10,000 Types Of Speaker Model Speaker dependent  ... 
doi:10.5120/ijca2017913130 fatcat:6uxrjp6ruzhchht5bxrv3f43xe
« Previous Showing results 1 — 15 out of 21,330 results