4,237 Hits in 4.2 sec

Leveraging phonetic context dependent invariant structure for continuous speech recognition

Congying Zhang, Masayuki Suzuki, Gakuto Kurata, Masafumi Nishimura, Nobuaki Minematsu
2014 2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP)  
The proposed method is tested in two tasks of continuous digits speech recognition and large vocabulary continuous speech recognition (LVCSR).  ...  In previous studies, the invariant structure was leveraged in continuous speech recognition for reranking the N-best candidates hypothesized by a traditional automatic speech recognition (ASR) system.  ...  This approach was applied both to isolated word recognition [2] [3] , and N-best candidates reranking for continuous speech recognition [4] [5] .  ... 
doi:10.1109/chinasip.2014.6889200 dblp:conf/chinasip/ZhangSKNM14 fatcat:24hxlcqdcvfi5ceusvyftnxzne

Acoustic Modelling for Croatian Speech Recognition and Synthesis

Sanda Martinčić–Ipšić, Slobodan Ribarić, Ivo Ipšić
2008 Informatica  
The proposed acoustic model is based on context-dependent triphone hidden Markov models and Croatian phonetic rules.  ...  The experiments have shown that Croatian speech corpus, Croatian phonetic rules and hidden Markov models as the modelling formalism can be used to develop speech recognition and speech synthesis systems  ...  The research reported here have been performed within the projects "Speech Technologies" and "Theory, Modelling and Application of Autonomy-Oriented Computing Structures" within the research program "Autonomy  ... 
doi:10.15388/informatica.2008.211 fatcat:4tgii4oc7vcctllxnkzfcmyv5u

Survey paper on Different Speech Recognition Algorithm: Challenges and Techniques

Ayushi Y., Krina A., Yesha A., Nirali Pandya
2017 International Journal of Computer Applications  
The challenges in speech recognition will be enumerated and analyzed for the most popular recognition techniques used today.  ...  The analysis ends with a brief description of some of the applications of speech recognition. General Terms Algorithms of Speech Recognition.  ...  Knowledge/Rule Based Approach Knowledge /rule based approach is used for continuous speech recognition which has been proposed by several researchers and applied to speech recognition.  ... 
doi:10.5120/ijca2017915472 fatcat:kxjo3modojhcjjzxvj5xz5mkoi

Improving Segment-based Speech Recognition by Recovering Missing Segments in Segment Graphs ¿ A Thai Case Study

Krerksak Likitsupin, Atiwong Suchato, Proadpran Punyabukkana, Chai Wutiwiwatchai
2008 2008 International Symposium on Communications and Information Technologies  
Acoustic discontinuities and manners of articulation are used to verify boundaries of the segment graph. Segments are added to the graph in the case of possible falsely detected boundaries.  ...  In segment-based speech recognition systems, the quality of the segmentation step is a major factor highly affecting their accuracies.  ...  ACKNOWLEDGEMENT Financial supports from Thailand Graduate Institute of Science and Technology (Grant no. TG-44-09-088D), are gratefully acknowledged.  ... 
doi:10.1109/iscit.2008.4700196 fatcat:xpcdyb5dpjbddiqoiflw3nilqa

Syllable-Based Speech Recognition System for Myanmar

Wunna Soe, Yadana Thein
2015 International Journal of Computer Science Engineering and Information Technology  
This proposed system is syllable-based Myanmar speech recognition system. There are three stages: Feature Extraction, Phone Recognition and Decoding.  ...  In feature extraction, the system transforms the input speech waveform into a sequence of acoustic feature vectors, each vector representing the information in a small time window of the signal.  ...  In other way, there are two types of speech recognition system: continuous speech recognition system, and isolated-word speech recognition system.  ... 
doi:10.5121/ijcseit.2015.5201 fatcat:ee6krim33jgrvpyb75a3tcweme

Large Vocabulary Arabic Continuous Speech Recognition using Tied States Acoustic Models

Mona A. Azim, A. Aziza Hamid, Nagwa L. Badr, M.F. Tolba
2019 Asian Journal of Information Technology  
The Hidden Markov Model (HMM) lies at the heart of the modern speech recognition systems as it provides a simple, effective and straight forward frame work to model the time varying acoustic features of  ...  The basic process of building HMM based speech recognition systems is a straight forward process. Nevertheless, the proper parameter estimation of such models requires large training data.  ...  The system obtained a word recognition In addition, an acoustic training system for speaker accuracy of 92.67 and 93.88% for similar speakers with independent continuous Arabic speech recognition different  ... 
doi:10.36478/ajit.2019.49.56 fatcat:5bpsrmykpzab5cd72jx7cp5e3i

Page 767 of Linguistics and Language Behavior Abstracts: LLBA Vol. 23, Issue 2 [page]

1989 Linguistics and Language Behavior Abstracts: LLBA  
para- digm proposed; 8903935 automatic speech recognition, networks of actions use paradigm pres- ented; 8903905 automatic speech recognition, P.  ...  Thatcher’s speech; 8903947 speech coding methods, perceptual evaluation; native-/nonnative En- glish speakers; 8903934 speech perception specialization; open vs closed modules; 8903924 speech recognition  ... 

Automated Transcription System for Malayalam Language

Cini Kurian, Kannan Balakrishnan
2011 International Journal of Computer Applications  
The system obtained a word recognition accuracy of 87.4% and a sentence recognition accuracy of 84%, when tested with a set of continuous speech data.  ...  The system employs Hidden Markov Model (HMM) for acoustic modeling and Mel Frequency Cepstral Coefficient (MFCC) for feature extraction.  ...  Sub-word unit selection and the creation of acoustic model are the two most important aspects in continuous speech recognition.  ... 
doi:10.5120/2360-3091 fatcat:ug4ap6vosreshghkbsqjh2j3lq

A Review on Acoustic Phonetic Approach for Marathi Speech Recognition

Rohini B.Shinde, V. P. Pawar
2012 International Journal of Computer Applications  
For this research a basic unit is ideally an output of acoustic-phonetic processing and an input to the lexical processing stages.  ...  For the purpose of the research described in this paper, a basic unit of speech recognition is the intermediate form of speech information around which much of the recognition processing is organized for  ...  So many problems are associated with the acoustic phonetic approach to speech recognition. 1. Recognition Rate for a word or the continuous speech is less. 2.  ... 
doi:10.5120/9523-3934 fatcat:efndusspmjeldds3fklgf5km5y

Computer-Aided Training for Quranic Recitation

Huda M. Arfan Tabbaa, Bassel Soudan
2015 Procedia - Social and Behavioral Sciences  
We have integrated Automatic Speech Recognition (ASR) and classifier-based approach to detect recitation errors.  ...  Error detection is done in two successive stages: first, an HMMbased ASR recognizes the recitation, detects the insertion, deletion and substitution of phones and provides phonetic time alignments, and  ...  The speech recognition process can be divided into three stages: 1. Feature extraction stage: The speech signal is transformed into a sequence of acoustic feature vectors.  ... 
doi:10.1016/j.sbspro.2015.06.092 fatcat:ejbfiztl3bfznmqh4yophu6fky

A Review on Speech Recognition Technique

Santosh K. Gaikwad, Bharti W. Gawali, Pravin Yannawar
2010 International Journal of Computer Applications  
and also gives overview technique developed in each stage of speech recognition.  ...  Speech has potential of being important mode of interaction with computer .This paper gives an overview of major technological perspective and appreciation of the fundamental progress of speech recognition  ...  The authors would like to thank the university authorities for Providing infrastructure to carry out the experiments. This work is supported by DST.  ... 
doi:10.5120/1462-1976 fatcat:zx4z3uczqjh2hhnrtc46b3rycu

Literature Review on Automatic Speech Recognition

Wiqas Ghai, Navdeep Singh
2012 International Journal of Computer Applications  
(ANN-HMM) have shown promise for large-vocabulary speech recognition systems.  ...  In this paper, an effort has been made to highlight the progress made so far for ASRs of different languages and the technological perspective of automatic speech recognition in countries like China, Russian  ...  The Artificial Intelligence approach is a hybrid of the acoustic phonetic approach and pattern recognition approach.  ... 
doi:10.5120/5565-7646 fatcat:wu46s3bhjbejhmskufomiodxma

Speech Recognition by Machine, A Review [article]

M. A. Anusuya, S. K. Katti
2010 arXiv   pre-print
of Speech Recognition system requires careful attentions to the following issues: Definition of various types of speech classes, speech representation, feature extraction techniques, speech classifiers  ...  , database and performance evaluation.  ...  IISc, Bangalore)and Dr.M.Narashima Murthuy, Prof. & Chairman, Dept. of CS & Automation, IISc., Bangalore, for their useful discussions and suggestions during the preparation of this technical paper.  ... 
arXiv:1001.2267v1 fatcat:yvcif2cb2jgkbjcqreid7cxanu

Automatic Speech Recognition: A Review

Shipra J.Arora, Rishi Pal Singh
2012 International Journal of Computer Applications  
The Speech recognition System focuses on difficulties with ASR, basic building blocks of speech processing, feature extraction, speech recognition and performance evaluation.  ...  techniques used in various stages of Speech recognition and identify research topic in this challenging field.  ...  Some researchers developed recognition system by using acoustic phonetic knowledge to develop classification rules for speech sounds.  ... 
doi:10.5120/9722-4190 fatcat:yvcakoseyvatlckusqnluumrka

Non-Native Pronunciation Variation Modeling for Automatic Speech Recognition [chapter]

Hong Kook, Mina Kim, Yoo Rhee
2010 Advances in Speech Recognition  
Third, pronunciation modeling approaches derive pronunciation variant rules from non-native speech and apply the derived rules to pronunciation models for non-native speech (Amdal et al.  ...  There have been three major approaches for handling non-native speech for ASR: acoustic modeling, language modeling, and pronunciation modeling approaches.  ...  The WSJ0 database was a 5000-word closed loop task for evaluating the performance of a large vocabulary continuous speech recognition (LVCSR) system.  ... 
doi:10.5772/10112 fatcat:omyy23c35fc3dhau3vcmvjlscu
« Previous Showing results 1 — 15 out of 4,237 results