Hindi and Punjabi Continuous Speech Recognition Using CNSVM

2019 ◽  
Vol 11 (4) ◽  
pp. 1-15
Author(s):  
Vishal Passricha ◽  
Shubhanshi Singhal
Keyword(s):  
Speech Recognition ◽  
Posterior Probability ◽  
Vital Role ◽  
Cross Entropy ◽  
High Dimensional ◽  
Hybrid Architecture ◽  
Continuous Speech Recognition ◽  
Speech Corpus ◽  
Word Error Rate ◽  
Classification Tasks

CNNs are playing a vital role in the field of automatic speech recognition. Most CNNs employ a softmax activation layer to minimize cross-entropy loss. This layer generates the posterior probability in object classification tasks. SVMs are also offering promising results in the field of ASR. In this article, two different approaches: CNNs and SVMs, are combined together to propose a new hybrid architecture. This model replaces the softmax layer, i.e. the last layer of CNN by SVMs to effectively deal with high dimensional features. This model should be interpreted as a special form of structured SVM and named the Convolutional Neural SVM. (CNSVM). CNSVMs incorporate the characteristics of both models which CNNs learn features from the speech signal and SVMs classify these features into corresponding text. The parameters of CNNs and SVMs are trained jointly using a sequence level max-margin and sMBR criterion. The performance achieved by CNSVM on Hindi and Punjabi speech corpus for word error rate is 13.43% and 15.86%, respectively, which is a significant improvement on CNNs.

scholarly journals JNAS: Japanese speech corpus for large vocabulary continuous speech recognition research.

1999 ◽  
Vol 20 (3) ◽  
pp. 199-206 ◽  
Author(s):  
Katunobu Itou ◽  
Mikio Yamamoto ◽  
Kazuya Takeda ◽  
Toshiyuki Takezawa ◽  
Tatsuo Matsuoka ◽  
...  
Keyword(s):  
Speech Recognition ◽  
Continuous Speech ◽  
Continuous Speech Recognition ◽  
Speech Corpus ◽  
Large Vocabulary

scholarly journals Creation and Instigation of Triphone based Big-Lexicon Speaker-Independent Continuous Speech Recognition Framework for Kannada Language

2019 ◽  
Vol 9 (2S) ◽  
pp. 152-158
Keyword(s):  
Speech Recognition ◽  
Recognition Rate ◽  
Continuous Speech ◽  
Continuous Speech Recognition ◽  
Mel Frequency Cepstral Coefficients ◽  
Speech Corpus ◽  
Linear Discriminant ◽  
Geographical Regions ◽  
Speech Data ◽  
Speech Information

This paper proposes a framework that is intended to do the comparably accurate recognition of speech and in precise, continuous speech recognition (CSR) based on triphone modelling for Kannada dialect. For designing the proposed framework, the features from the speech data are obtained from the well-known feature extraction technique Mel-frequency cepstral coefficients (MFCC) and from its transformations, like, linear discriminant analysis (LDA) and maximum likelihood linear transforms (MLLT) are obtained from Kannada speech data files. At that point, the system is trained to evaluate the hidden Markov model (HMM) parameters for continuous speech (CS) data. The persistent Kannada speech information is gathered from 2600 speakers (1560 men and 1040women) of the age bunch in the scope of 14 years-80 years. The speech information is acquired from different geographical regions of the Karnataka (one of the 29 states situated in the southern part of India) state under degraded condition. It comprises of 21,551 words that spread 30 locales. The performance evaluation of both monophone and triphone models concerning word error rate (WER) is done and the obtained results are compared with the standard databases such as TIMIT and aurora4. A significant reduction in WER is obtained for triphone models. The speech recognition (SR) rate is verified for both offline and online recognition mode for all the speakers. The results reveal that the recognition rate (RR) for Kannada speech corpus has got a better improvement over the state-of-the-art existing databases.

scholarly journals A Hybrid of Deep CNN and Bidirectional LSTM for Automatic Speech Recognition

2019 ◽  
Vol 29 (1) ◽  
pp. 1261-1274 ◽  
Author(s):  
Vishal Passricha ◽  
Rajesh Kumar Aggarwal
Keyword(s):  
Neural Networks ◽  
Speech Recognition ◽  
Speech Signal ◽  
Short Term Memory ◽  
Recognition Rate ◽  
Recognition Task ◽  
Acoustic Modeling ◽  
Hybrid Architecture ◽  
Continuous Speech Recognition ◽  
Temporal Properties

Abstract Deep neural networks (DNNs) have been playing a significant role in acoustic modeling. Convolutional neural networks (CNNs) are the advanced version of DNNs that achieve 4–12% relative gain in the word error rate (WER) over DNNs. Existence of spectral variations and local correlations in speech signal makes CNNs more capable of speech recognition. Recently, it has been demonstrated that bidirectional long short-term memory (BLSTM) produces higher recognition rate in acoustic modeling because they are adequate to reinforce higher-level representations of acoustic data. Spatial and temporal properties of the speech signal are essential for high recognition rate, so the concept of combining two different networks came into mind. In this paper, a hybrid architecture of CNN-BLSTM is proposed to appropriately use these properties and to improve the continuous speech recognition task. Further, we explore different methods like weight sharing, the appropriate number of hidden units, and ideal pooling strategy for CNN to achieve a high recognition rate. Specifically, the focus is also on how many BLSTM layers are effective. This paper also attempts to overcome another shortcoming of CNN, i.e. speaker-adapted features, which are not possible to be directly modeled in CNN. Next, various non-linearities with or without dropout are analyzed for speech tasks. Experiments indicate that proposed hybrid architecture with speaker-adapted features and maxout non-linearity with dropout idea shows 5.8% and 10% relative decrease in WER over the CNN and DNN systems, respectively.

scholarly journals Building Acoustic and Language Model for Continuous Speech Recognition in Bahasa Indonesia

2020 ◽  
Vol 6 (2) ◽  
Author(s):  
Vincent Elbert Budiman ◽  
Andreas Widjaja
Keyword(s):  
Speech Recognition ◽  
Error Rate ◽  
Language Model ◽  
Beam Width ◽  
Acoustic Model ◽  
Continuous Speech ◽  
Continuous Speech Recognition ◽  
Word Error Rate ◽  
Testing Data ◽  
Bahasa Indonesia

Here a development of an Acoustic and Language Model is presented. Low Word Error Rate is an early good sign of a good Language and Acoustic Model. Although there are still parameters other than Words Error Rate, our work focused on building Bahasa Indonesia with approximately 2000 common words and achieved the minimum threshold of 25% Word Error Rate. There were several experiments consist of different cases, training data, and testing data with Word Error Rate and Testing Ratio as the main comparison. The language and acoustic model were built using Sphinx4 from Carnegie Mellon University using Hidden Markov Model for the acoustic model and ARPA Model for the language model. The models configurations, which are Beam Width and Force Alignment, directly correlates with Word Error Rate. The configurations were set to 1e-80 for Beam Width and 1e-60 for Force Alignment to prevent underfitting or overfitting of the acoustic model. The goals of this research are to build continuous speech recognition in Bahasa Indonesia which has low Word Error Rate and to determine the optimum numbers of training and testing data which minimize the Word Error Rate.  

scholarly journals Continuous Speech Recognition of Kazakh Language

2019 ◽  
Vol 24 ◽  
pp. 01012 ◽  
Author(s):  
Оrken Mamyrbayev ◽  
Mussa Turdalyuly ◽  
Nurbapa Mekebayev ◽  
Kuralay Mukhsina ◽  
Alimukhan Keylan ◽  
...  
Keyword(s):  
Neural Networks ◽  
Speech Recognition ◽  
Error Rate ◽  
Speech Signal ◽  
Deep Neural Networks ◽  
Continuous Speech ◽  
Continuous Speech Recognition ◽  
Reliable System ◽  
Word Error Rate ◽  
Language Studies

This article describes the methods of creating a system of recognizing the continuous speech of Kazakh language. Studies on recognition of Kazakh speech in comparison with other languages began relatively recently, that is after obtaining independence of the country, and belongs to low resource languages. A large amount of data is required to create a reliable system and evaluate it accurately. A database has been created for the Kazakh language, consisting of a speech signal and corresponding transcriptions. The continuous speech has been composed of 200 speakers of different genders and ages, and the pronunciation vocabulary of the selected language. Traditional models and deep neural networks have been used to train the system. As a result, a word error rate (WER) of 30.01% has been obtained.

Sign in / Sign up

Export Citation Format

Share Document