Filters








69,542 Hits in 5.9 sec

Automatic Speech Recognition: An Improved Paradigm [chapter]

Tudor-Sabin Topoleanu, Gheorghe Leonte Mogan
2011 IFIP Advances in Information and Communication Technology  
In response to which we propose an improved paradigm and algorithm for building an automatic speech recognition system that actively adapts its recognition model in an unsupervised fashion by listening  ...  Finally we provide the structure and algorithms for this novel automatic speech recognition paradigm.  ...  In this paper we propose an algorithm and structure for an automatic speech recognition system that allows semi-autonomous acquisition of speech recognition.  ... 
doi:10.1007/978-3-642-19170-1_29 fatcat:6odgiqqfqrh5nf2pdejcqzckge

An Investigation into Methodology and Metrics Employed to Evaluate the (Speech-to-Speech) Way in Translation Systems

Parnyan Bahrami Dashtaki
2017 Modern Applied Science  
Many procedures for incorporation of speech recognition and machine translation have been projected.  ...  Under this general framework, some specific models are presented. One of the features of such models is their capability of automatically learning from training examples.  ...  The supplementary information can be exploited by a tight coupling of speech recognition and machine translation (Ney, 1999) or keeping the cascaded structure unchanged but using an integration model  ... 
doi:10.5539/mas.v11n4p55 fatcat:r365jxnz5bdgxhfo6fexkhorxm

On model architecture for a children's speech recognition interactive dialog system [article]

Radoslava Kraleva, Velin Kralev
2016 arXiv   pre-print
This report presents a general model of the architecture of information systems for the speech recognition of children. It presents a model of the speech data stream and how it works.  ...  Another important aspect is the development of more accurate algorithms for modeling of spontaneous child speech.  ...  in children Fig. 1 : 1 Schematic structure of the basic steps of an automatic speech recognition system Fig. 2 : 2 Schematic structure of the basic steps of an automatic speech recognition system  ... 
arXiv:1605.07733v1 fatcat:sc4cdnqponbirmdugbnjw3wivu

Content-based Language Models for Spoken Document Retrieval

HSIN-MIN WANG, BERLIN CHEN
2001 International Journal of Computer Processing Of Languages  
In an example task for retrieval of Mandarin Chinese broadcast news data, the content-based language models either trained on automatic transcriptions of spoken documents or adapted from baseline language  ...  models using automatic transcriptions of spoken documents were used to create more accurate recognition results and indexing terms from both spoken documents and speech queries.  ...  Acknowledgments The authors wish to thank the National Science Council of the Republic of China for financially supporting this research under Contract No. NSC 89-2213-E-001-049.  ... 
doi:10.1142/s0219427901000333 fatcat:zvb5fbwd6zaubbb64lrnd2pngm

Content-based language models for spoken document retrieval

Hsin-min Wang, Berlin Chen
2000 Proceedings of the fifth international workshop on on Information retrieval with Asian languages - IRAL '00  
In an example task for retrieval of Mandarin Chinese broadcast news data, the content-based language models either trained on automatic transcriptions of spoken documents or adapted from baseline language  ...  models using automatic transcriptions of spoken documents were used to create more accurate recognition results and indexing terms from both spoken documents and speech queries.  ...  Acknowledgments The authors wish to thank the National Science Council of the Republic of China for financially supporting this research under Contract No. NSC 89-2213-E-001-049.  ... 
doi:10.1145/355214.355236 dblp:conf/iral/WangC00 fatcat:skg6e6mx6fgtppwfeenxfwvhgu

Perceptual and Automatic Evaluations of the Intelligibility of Speech Degraded by Noise Induced Hearing Loss Simulation

Imed Laaridh, Julien Tardieu, Cynthia Magnen, Pascal Gaillard, Jérôme Farinas, Julien Pinquier
2018 Interspeech 2018  
Then, an Automatic Speech Recognition (ASR) system has been designed to predict the perceptual scores of intelligibility.  ...  In addition, the automatic intelligibility measure, based on automatic speech recognition scores, was proven to well predict the effects of the different severity levels of NIHL.  ...  Figure 5 depicts the mean automatic and perceptual recognition rates for the 3 speakers per simulated degradation level using the different language model/lexicon configurations for the sentence recognition  ... 
doi:10.21437/interspeech.2018-1264 dblp:conf/interspeech/LaaridhTMGFP18 fatcat:yp6a3c6erfgoxilsjy5obfdh4q

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  
Moreover, the article delivers information about the speech corpus structure and contents and also a brief outline of the design and architecture of the automatic speech recognition system.  ...  In this study, the results of acoustic modeling used in a large vocabulary continuous speech recognition system are presented.  ...  Acknowledgments 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  ... 
doi:10.12693/aphyspola.121.a-86 fatcat:wjznaujp6jae3fqp2d5ffhzimy

Creation of Language Resources for the Development of a Medical Speech Recognition System for Latvian

Roberts Dargis, Normunds Gruzitis, Ilze Auzina, Kaspars Stepanovs
2020 Human Language Technology - The Baltic Perspectiv  
The language resources include a pronunciation lexicon, a text corpus for language modelling, and an orthographically transcribed speech corpus for the (i) adaptation of the acoustic model, (ii) evaluation  ...  This paper describes an ongoing work on the creation of Latvian language resources for the medical domain focusing on digital imaging to develop a medical speech recognition system for Latvian.  ...  lexicon of medical terms, abbreviations and named entities for their recognition and consistent transcription; an anonymised and orthographically transcribed speech corpus for adapting the acoustic model  ... 
doi:10.3233/faia200615 dblp:conf/hlt/DargisGAS20 fatcat:w32xnll3jvfn3kjjjktc4niac4

On Spoken English Phoneme Evaluation Method Based on Sphinx-4 Computer System

Li Qin
2017 International Journal of Emerging Technologies in Learning (iJET)  
Then it proposes an HDP evaluation model, which integrates the reliability of the speech processing system and the individualization of spoken English learners into the evaluation system.  ...  This paper studies a speech phoneme evaluation method for HDPs, hoping to improve the ability of individualized evaluation on HDPs and help provide a personalized learning platform for English learners  ...  Language processing technology The development of computer technology and voice processing technology provides new ideas for automatic speech recognition.  ... 
doi:10.3991/ijet.v12i12.7957 fatcat:3tkuw3wx3bct7pk57ztkqiu77e

Cross-lingual audio-to-text alignment for multimedia content management

Dau-Cheng Lyu, Ren-Yuan Lyu, Yuang-Chin Chiang, Chun-Nan Hsu
2008 Decision Support Systems  
Due to the lack of a standard written form for Taiwanese, manual transcription of spoken documents is prohibitively expensive, and automatic transcription by speech recognition is infeasible because of  ...  The idea is to take advantage of the abundance of Mandarin text documents available in our application to compensate for the limitations of speech recognition systems.  ...  As mentioned in Section 4.2, we need a text corpus to train the language model in order to improve automatic speech recognition of spontaneous speech.  ... 
doi:10.1016/j.dss.2007.07.003 fatcat:t5seflrjifcolnrouwvb6d2sge

TEDxSK and JumpSK: A New Slovak Speech Recognition Dedicated Corpus

Ján Staš, Daniel Hládek, Peter Viszlay, Tomáš Koctúr
2017 Jazykovedný Časopis  
The evaluation data consisting of 50 manually annotated talks and lectures in total duration of about 12 hours, has been created for evaluation of the quality of Slovak speech recognition.  ...  Annotated speech database was generated automatically in an unsupervised manner by using acoustic speech segmentation based on principal component analysis and automatic speech transcription using two  ...  AcKNOWLEDGEMENtS The research in this paper was supported by the faculty of Electrical Engineering and  ... 
doi:10.1515/jazcas-2017-0044 fatcat:edxsozbcynhmzdvk3xu54hvzou

PARSE STRUCTURE AND SEGMENTATION FOR IMPROVING SPEECH RECOGNITION

William Mcneill, Jeremy Kahn, Dustin Hillard, Mari Ostendorf
2006 2006 IEEE Spoken Language Technology Workshop  
Separate avenues of prior work have shown that parsing language models lead to improved recognition performance, and that segmentation of speech into sentence-like units has an impact on parser performance  ...  This paper brings these two findings together, showing that segmentation also impacts the quality of a syntax-based language model, such that larger reductions in word error rate are possible when using  ...  These results raise the question of how effective parsing language models are for speech recognition with pause-based vs. automatic sentence segmentation.  ... 
doi:10.1109/slt.2006.326824 dblp:conf/slt/McNeillKHO06 fatcat:q2llsqrrcjduzd7it274orhf7y

The VoiceTRAN Speech-to-Speech Communicator [chapter]

Jerneja Žganec-Gros, France Mihelič, Tomaž Erjavec, Špela Vintar
2005 Lecture Notes in Computer Science  
We conclude the paper with plans for evaluation of the VoiceTRAN Communicator.  ...  The paper presents the design concept of the VoiceTRAN Communicator that integrates speech recognition, machine translation and text-to-speech synthesis using the DARPA Galaxy architecture.  ...  Acknowledgements The authors of the paper thank the Slovenian Ministry of Defense and the Slovenian Ministry of Higher Education, Science and Technology for co-funding the project.  ... 
doi:10.1007/11551874_49 fatcat:2mrbuwd57vel3bw362evditpny

Integrating different learning approaches into a multilingual spoken language translation system [chapter]

P. Geutner, B. Suhm, F. -D. Buø, T. Kemp, L. Mayfield, A. E. McNair, I. Rogina, T. Schultz, T. Sloboda, W. Ward, M. Woszczyna, A. Waibel
1996 Lecture Notes in Computer Science  
In this paper we will present learning techniques that improve acoustic models by automatically adapting codebook sizes, a learning algorithm that increases and adapts phonetic dictionaries for the recognition  ...  Getting optimal acoustic and language models as well as developing adequate dictionaries for all these languages requires a lot of hand-tuning and is time-consuming and labor intensive.  ...  We have developed a speech interface for repairing recognition errors by simply respeaking or spelling a misrecognized section of an utterance.  ... 
doi:10.1007/3-540-60925-3_42 fatcat:gvgbvudr5vfcfikdhnhoh42z5a

Phone based acoustic modeling for automatic speech recognition for Punjabi language

Wiqas Ghai, Navdeep Singh
2021 Journal of Speech Sciences  
Some work has been done in the field of isolated word speech recognition for Punjabi language, but only using whole word based acoustic models.  ...  Word recognition accuracy of isolated word speech was 92.05% for acoustic whole word model based system and 97.14% for acoustic triphone model based system whereas word recognition accuracy of connected  ...  Knowledge Models An automatic speech recognition system requires the capability to know how the words sound. Knowledge models are meant for mapping a sound to a word/phrase.  ... 
doi:10.20396/joss.v3i1.15040 fatcat:syo2xc5dyveddetcrk2yj6vrvq
« Previous Showing results 1 — 15 out of 69,542 results