scholarly journals Building a Speech and Text Corpus of Turkish: Large Corpus Collection with Initial Speech Recognition Results

Symmetry ◽  
2020 ◽  
Vol 12 (2) ◽  
pp. 290 ◽  
Author(s):  
Huseyin Polat ◽  
Saadin Oyucu
Keyword(s):  
Speech Recognition ◽  
Language Model ◽  
Recognition Task ◽  
Gaussian Mixture ◽  
Speech Corpus ◽  
Text Corpus ◽  
Training Models ◽  
Relative Contribution ◽  
The Status ◽  
Asr System

To build automatic speech recognition (ASR) systems with a low word error rate (WER), a large speech and text corpus is needed. Corpus preparation is the first step required for developing an ASR system for a language with few argument speech documents available. Turkish is a language with limited resources for ASR. Therefore, development of a symmetric Turkish transcribed speech corpus according to the high resources languages corpora is crucial for improving and promoting Turkish speech recognition activities. In this study, we constructed a viable alternative to classical transcribed corpus preparation techniques for collecting Turkish speech data. In the presented approach, three different methods were used. In the first step, subtitles, which are mainly supplied for people with hearing difficulties, were used as transcriptions for the speech utterances obtained from movies. In the second step, data were collected via a mobile application. In the third step, a transfer learning approach to the Grand National Assembly of Turkey session records (videotext) was used. We also provide the initial speech recognition results of artificial neural network and Gaussian mixture-model-based acoustic models for Turkish. For training models, the newly collected corpus and other existing corpora published by the Linguistic Data Consortium were used. In light of the test results of the other existing corpora, the current study showed the relative contribution of corpus variability in a symmetric speech recognition task. The decrease in WER after including the new corpus was more evident with increased verified data size, compensating for the status of Turkish as a low resource language. For further studies, the importance of the corpus and language model in the success of the Turkish ASR system is shown.

Improving Deep Learning based Automatic Speech Recognition for Gujarati

2022 ◽  
Vol 21 (3) ◽  
pp. 1-18
Author(s):  
Deepang Raval ◽  
Vyom Pathak ◽  
Muktan Patel ◽  
Brijesh Bhatt
Keyword(s):  
Deep Learning ◽  
Speech Recognition ◽  
Automatic Speech Recognition ◽  
Short Term Memory ◽  
Language Model ◽  
Recognition System ◽  
Processing Technique ◽  
Speech Corpus ◽  
Novel Approach ◽  
Asr System

We present a novel approach for improving the performance of an End-to-End speech recognition system for the Gujarati language. We follow a deep learning-based approach that includes Convolutional Neural Network, Bi-directional Long Short Term Memory layers, Dense layers, and Connectionist Temporal Classification as a loss function. To improve the performance of the system with the limited size of the dataset, we present a combined language model (Word-level language Model and Character-level language model)-based prefix decoding technique and Bidirectional Encoder Representations from Transformers-based post-processing technique. To gain key insights from our Automatic Speech Recognition (ASR) system, we used the inferences from the system and proposed different analysis methods. These insights help us in understanding and improving the ASR system as well as provide intuition into the language used for the ASR system. We have trained the model on the Microsoft Speech Corpus, and we observe a 5.87% decrease in Word Error Rate (WER) with respect to base-model WER.

scholarly journals Automatic Speech Recognition (ASR) System for Isolated Marathi Words: using HTK

2019 ◽  
Vol 8 (12) ◽  
pp. 3702-3705
Keyword(s):  
Speech Recognition ◽  
Automatic Speech Recognition ◽  
Viterbi Algorithm ◽  
Gaussian Mixture ◽  
Speech Corpus ◽  
Word Level ◽  
Speaker Independent ◽  
Token Passing ◽  
Mel Frequency Cepstral Coefficient ◽  
Asr System

The present manuscript focuses on building automatic speech recognition (ASR) system for Marathi language (M-ASR) using Hidden Markov Model Toolkit (HTK). The M-ASR system gives the detail about experimentation and implementation using the HTK Toolkit. In this work total 106 speaker independent Marathi isolated words were recognized. These unique Marathi words are used to train and evaluate M-ASR system. The speech corpus (database) is created by us using isolated Marathi words uttered with mixed gender people. The system uses Mel Frequency Cepstral Coefficient (MFCC) for the purpose of extracting features using Gaussian mixture model (GMM). Viterbi algorithm based on token passing is used for decoding to recognize unknown utterances. The proposed M-ASR system is speaker independent. The proposed system has reported 96.23% word level recognition accuracy.

scholarly journals UCSY-SC1: A Myanmar speech corpus for automatic speech recognition

2019 ◽  
Vol 9 (4) ◽  
pp. 3194 ◽  
Author(s):  
Aye Nyein Mon ◽  
Win Pa Pa ◽  
Ye Kyaw Thu
Keyword(s):  
Neural Network ◽  
Speech Recognition ◽  
Automatic Speech Recognition ◽  
Gaussian Mixture ◽  
Error Rates ◽  
Training Data ◽  
Speech Corpus ◽  
Total Size ◽  
Test Sets ◽  
Web News

This paper introduces a speech corpus which is developed for Myanmar Automatic Speech Recognition (ASR) research. Automatic Speech Recognition (ASR) research has been conducted by the researchers around the world to improve their language technologies. Speech corpora are important in developing the ASR and the creation of the corpora is necessary especially for low-resourced languages. Myanmar language can be regarded as a low-resourced language because of lack of pre-created resources for speech processing research. In this work, a speech corpus named UCSY-SC1 (University of Computer Studies Yangon - Speech Corpus1) is created for Myanmar ASR research. The corpus consists of two types of domain: news and daily conversations. The total size of the speech corpus is over 42 hrs. There are 25 hrs of web news and 17 hrs of conversational recorded data.<br />The corpus was collected from 177 females and 84 males for the news data and 42 females and 4 males for conversational domain. This corpus was used as training data for developing Myanmar ASR. Three different types of acoustic models  such as Gaussian Mixture Model (GMM) - Hidden Markov Model (HMM), Deep Neural Network (DNN), and Convolutional Neural Network (CNN) models were built and compared their results. Experiments were conducted on different data  sizes and evaluation is done by two test sets: TestSet1, web news and TestSet2, recorded conversational data. It showed that the performance of Myanmar ASRs using this corpus gave satisfiable results on both test sets. The Myanmar ASR  using this corpus leading to word error rates of 15.61% on TestSet1 and 24.43% on TestSet2.<br /><br />

Mandarin Electrolaryngeal Speech Recognition Based on WaveNet-CTC

2019 ◽  
Vol 62 (7) ◽  
pp. 2203-2212
Author(s):  
Zhaopeng Qian ◽  
Li Wang ◽  
Shaochuan Zhang ◽  
Chan Liu ◽  
Haijun Niu
Keyword(s):  
Speech Recognition ◽  
Language Model ◽  
Chinese Characters ◽  
Acoustic Features ◽  
Traditional Methods ◽  
Radiation Noise ◽  
New Perspective ◽  
Deep Learning Model ◽  
Asr System ◽  
Chinese Mandarin

Purpose The application of Chinese Mandarin electrolaryngeal (EL) speech for laryngectomees has been limited by its drawbacks such as single fundamental frequency, mechanical sound, and large radiation noise. To improve the intelligibility of Chinese Mandarin EL speech, a new perspective using the automatic speech recognition (ASR) system was proposed, which can convert EL speech into healthy speech, if combined with text-to-speech. Method An ASR system was designed to recognize EL speech based on a deep learning model WaveNet and the connectionist temporal classification (WaveNet-CTC). This system mainly consists of 3 parts: the acoustic model, the language model, and the decoding model. The acoustic features are extracted during speech preprocessing, and 3,230 utterances of EL speech mixed with 10,000 utterances of healthy speech are used to train the ASR system. Comparative experiment was designed to evaluate the performance of the proposed method. Results The results show that the proposed ASR system has higher stability and generalizability compared with the traditional methods, manifesting superiority in terms of Chinese characters, Chinese words, short sentences, and long sentences. Phoneme confusion occurs more easily in the stop and affricate of EL speech than the healthy speech. However, the highest accuracy of the ASR could reach 83.24% when 3,230 utterances of EL speech were used to train the ASR system. Conclusions This study indicates that EL speech could be recognized effectively by the ASR based on WaveNet-CTC. This proposed method has a higher generalization performance and better stability than the traditional methods. A higher accuracy of the ASR system based on WaveNet-CTC can be obtained, which means that EL speech can be converted into healthy speech. Supplemental Material https://doi.org/10.23641/asha.8250830

Performance Analysis of various Front-end and Back End Amalgamations for Noise-robust DNN-based ASR

2020 ◽  
Vol 13 ◽  
Author(s):  
Mohit Dua ◽  
Pawandeep Singh Sethi ◽  
Vinam Agrawal ◽  
Raghav Chawla
Keyword(s):  
Feature Extraction ◽  
Speech Recognition ◽  
Automatic Speech Recognition ◽  
Gaussian Mixture ◽  
Performance Comparison ◽  
Acoustic Modeling ◽  
Extraction Techniques ◽  
Front End ◽  
Noise Robust ◽  
Asr System

Introduction: An Automatic Speech Recognition (ASR) system enables to recognize the speech utterances and thus can be used to convert speech into text for various purposes. These systems are deployed in different environments such as clean or noisy and are used by all ages or types of people. These also present some of the major difficulties faced in the development of an ASR system. Thus, an ASR system need to be efficient, while also being accurate and robust. Our main goal is to minimize the error rate during training as well as testing phases, while implementing an ASR system. Performance of ASR depends upon different combinations of feature extraction techniques and back-end techniques. In this paper, using a continuous speech recognition system, the performance comparison of different combinations of feature extraction techniques and various types of back-end techniques has been presented Methods: Hidden Markov Models (HMMs), Subspace Gaussian Mixture Models (SGMMs) and Deep Neural Networks (DNNs) with DNN-HMM architecture, namely Karel's, Dan's and Hybrid DNN-SGMM architecture are used at the back-end of the implemented system. Mel frequency Cepstral Coefficient (MFCC), Perceptual Linear Prediction (PLP), and Gammatone Frequency Cepstral coefficients (GFCC) are used as feature extraction techniques at the front-end of the proposed system. Kaldi toolkit has been used for the implementation of the proposed work. The system is trained on the Texas Instruments-Massachusetts Institute of Technology (TIMIT) speech corpus for English language Results: The experimental results show that MFCC outperforms GFCC and PLP in noiseless conditions, while PLP tends to outperform MFCC and GFCC in noisy conditions. Furthermore, the hybrid of Dan's DNN implementation along with SGMM performs the best for the back-end acoustic modeling. The proposed architecture with PLP feature extraction technique in the front end and hybrid of Dan's DNN implementation along with SGMM at the back end outperforms the other combinations in a noisy environment. Conclusion: Automatic Speech recognition has numerous applications in our lives like Home automation, Personal assistant, Robotics etc. It is highly desirable to build an ASR system with good performance. The performance Automatic Speech Recognition is affected by various factors which include vocabulary size, whether system is speaker dependent or independent, whether speech is isolated, discontinuous or continuous, adverse conditions like noise. The paper presented an ensemble architecture that uses PLP for feature extraction at the front end and a hybrid of SGMM + Dan's DNN in the backend to build a noise robust ASR system Discussion: The presented work in this paper discusses the performance comparison of continuous ASR systems developed using different combinations of front-end feature extraction (MFCC, PLP, and GFCC) and back-end acoustic modeling (mono-phone, tri-phone, SGMM, DNN and hybrid DNN-SGMM) techniques. Each type of front-end technique is tested in combination with each type of back-end technique. Finally, it compares the results of the combinations thus formed, to find out the best performing combination in noisy and clean conditions

scholarly journals Automatic Speech Recognition Systems for Regional Languages in India

2019 ◽  
Vol 8 (2S3) ◽  
pp. 585-592
Keyword(s):  
Speech Recognition ◽  
Service Sector ◽  
English Language ◽  
Language Model ◽  
Recognition Systems ◽  
Tools And Techniques ◽  
Regional Languages ◽  
Directory Services ◽  
Remarkable Progress ◽  
Asr System

Speech recognition systems has made remarkable progress in last ¬few decades such as Siri, Google assistant, Cortana. For improving the automation in services of all sectors including medical, agriculture, voice dialling, directory services, education, automobile etc., ASR systems must be built for regional languages as most of the Indian population in not familiar with English. Lots of work is done for English language but not for regional languages in India. Developing ASR and ASU systems will change the scenario of current service sector. There are many challenges in building ASR system, Noise reduction is a one of the challenging and still unsolved parameters which affects a lot on performance of any ASR system. Basically, three models required for building any ASR systems- Language model, acoustic model and pronunciation model. In this paper, discussed various parameters affecting on building ASR systems, development of ASR systems, Tools and Techniques used for building an ASR system and research on regional languages ASR system. Deep Neural network (DNN) provides a better way of recognising a speech and accuracy is high.

scholarly journals The Relevance of the Source Language in Transfer Learning for ASR

2021 ◽  
Vol 1 (2) ◽  
Author(s):  
Nils Hjortnæs ◽  
Niko Partanen ◽  
Michael Rießler ◽  
Francis M. Tyers
Keyword(s):  
Speech Recognition ◽  
Transfer Learning ◽  
Close Contact ◽  
Language Model ◽  
Model Construction ◽  
Russian Text ◽  
Language Documentation ◽  
Speech Corpus ◽  
Source Language

This study presents new experiments on Zyrian Komi speech recognition. We use Deep-Speech to train ASR models from a language documentation corpus that contains both contemporary and archival recordings. Earlier studies have shown that transfer learning from English and using a domain matching Komi language model both improve the CER and WER. In this study we experiment with transfer learning from a more relevant source language, Russian, and including Russian text in the language model construction. The motivation for this is that Russian and Komi are contemporary contact languages, and Russian is regularly present in the corpus. We found that despite the close contact of Russian and Komi, the size of the English speech corpus yielded greater performance when used as the source language. Additionally, we can report that already an update in DeepSpeech version improved the CER by 3.9% against the earlier studies, which is an important step in the development of Komi ASR.

scholarly journals Discriminatively trained continuous Hindi speech recognition using integrated acoustic features and recurrent neural network language modeling

2020 ◽  
Vol 30 (1) ◽  
pp. 165-179
Author(s):  
A. Kumar ◽  
R.K. Aggarwal
Keyword(s):  
Neural Network ◽  
Speech Recognition ◽  
Maximum Likelihood ◽  
Linear Regression ◽  
Recurrent Neural Network ◽  
Gaussian Mixture ◽  
Language Modeling ◽  
Baseline System ◽  
Maximum Likelihood Linear Regression ◽  
Asr System

Abstract This paper implements the continuous Hindi Automatic Speech Recognition (ASR) system using the proposed integrated features vector with Recurrent Neural Network (RNN) based Language Modeling (LM). The proposed system also implements the speaker adaptation using Maximum-Likelihood Linear Regression (MLLR) and Constrained Maximum likelihood Linear Regression (C-MLLR). This system is discriminatively trained by Maximum Mutual Information (MMI) and Minimum Phone Error (MPE) techniques with 256 Gaussian mixture per Hidden Markov Model(HMM) state. The training of the baseline system has been done using a phonetically rich Hindi dataset. The results show that discriminative training enhances the baseline system performance by up to 3%. Further improvement of ~7% has been recorded by applying RNN LM. The proposed Hindi ASR system shows significant performance improvement over other current state-of-the-art techniques.

scholarly journals Lithuanian Speech Recognition Using Purely Phonetic Deep Learning

Computers ◽  
2019 ◽  
Vol 8 (4) ◽  
pp. 76 ◽  
Author(s):  
Laurynas Pipiras ◽  
Rytis Maskeliūnas ◽  
Robertas Damaševičius
Keyword(s):  
Deep Learning ◽  
Speech Recognition ◽  
Automatic Speech Recognition ◽  
Recognition Task ◽  
Data Models ◽  
Attention Mechanism ◽  
Large Majority ◽  
Learning Methods ◽  
Language Structure ◽  
Asr System

Automatic speech recognition (ASR) has been one of the biggest and hardest challenges in the field. A large majority of research in this area focuses on widely spoken languages such as English. The problems of automatic Lithuanian speech recognition have attracted little attention so far. Due to complicated language structure and scarcity of data, models proposed for other languages such as English cannot be directly adopted for Lithuanian. In this paper we propose an ASR system for the Lithuanian language, which is based on deep learning methods and can identify spoken words purely from their phoneme sequences. Two encoder-decoder models are used to solve the ASR task: a traditional encoder-decoder model and a model with attention mechanism. The performance of these models is evaluated in isolated speech recognition task (with an accuracy of 0.993) and long phrase recognition task (with an accuracy of 0.992).

scholarly journals Performance of Isolated and Continuous Digit Recognition System using Kaldi Toolkit

2019 ◽  
Vol 8 (2S2) ◽  
pp. 264-271
Keyword(s):  
System Performance ◽  
Recognition Accuracy ◽  
Language Model ◽  
Recognition Task ◽  
Recognition System ◽  
Feature Representation ◽  
Speech Corpus ◽  
Word Error Rate ◽  
Hybrid Classifier ◽  
Digit Recognition

A digit recognition system is built for recognizing the sequence of digits through 0-9. The system is experimented with speech corpus created in the room environment. The acoustic information to feature representation is achieved using PLP and MFCC features. The system initially utilized the conventional GMM-HMM framework, state of the art hybrid classifier with varied number of states to complete the speech recognition task, i.e., the system is first trained and tested using Monophone models, and system’s recognition accuracy is then evaluated using Triphone Models: Triphone1 models, which was later followed by Triphones2 models and Triphones3 Models. The Ngram Language model is used for both Monophone and Triphone training. The system performance is evaluated with the use of MFCC and PLP parameterisation techniques on Kaldi toolkit. The system performance is evaluated using metrics word error rate (WER) and Word Recognition Accuracy (WRA). The proposed system can be utilized for building speech applications

Sign in / Sign up

Export Citation Format

Share Document