Turkish speech corpora and recognition tools developed by porting SONIC: Towards multilingual speech recognition

Salor, Özgül; Pellom, Bryan L.; Çiloğlu, Tolga; Demirekler, Mübeccel

doi:10.1016/j.csl.2007.01.001

Cited by 27 publications

(38 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Some works have also been reported on Asian tone languages such as Mandarin [6,14,16,19,23,31,32] Cantonese [15,21,22,25,63] and Thai [39,59]. Ray and Ghoshal [26] have also reported the development an ASR for vowels of three Indian languages, namely: Telugu, Assamese and Bengali and Salor et al [60] have reported works on Turkish.…”

Section: Introductionmentioning

confidence: 92%

Automatic recognition of oral vowels in tone language: Experiments with fuzzy logic and neural network models

íkínbí

Odéjobí

2011

Applied Soft Computing

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 92%

Automatic recognition of oral vowels in tone language: Experiments with fuzzy logic and neural network models

íkínbí

Odéjobí

2011

Applied Soft Computing

View full text Add to dashboard Cite

“…After the preparation of the text dataset, it is necessary to prepare an audio dataset. In this study, audio data of Middle East Technical University Microphone Speech v 1.0 [36,37] was used. It is a dataset prepared in Turkish language.…”

Section: Data Preparation Phasementioning

confidence: 99%

“…In testing phase, an exemplary speech recognition model in RNN-LSTM structure was created. METU 1.0 Turkish speech set, which was suggested in the studies [36,37] and distributed over Linguistic Data Consortium (LDC) [39], was used for training of the model. The outputs of the standard recognition model were subjected to the comparison model process, of which the details are in Figure 5, and an increase in system performance was intended to be achieved.…”

Section: Testing Phasementioning

confidence: 99%

Development of Output Correction Methodology for Long Short Term Memory-Based Speech Recognition

Arslan

Barışçı

2019

Sustainability

View full text Add to dashboard Cite

This paper presents a correction methodology for Long Short Term Memory (LSTM) based speech recognition. A strategy that validates with a reference database was developed for LSTM. It is conceptually simple but requires a large keyword database to match test templates. The correction method is based on the “most matching method” that is finding the word in which the system output is closest among the “Referenced Template Database”. Each LSTM model recognition output was corrected with the proposed new concept. Thus, system recognition performance was improved by correcting faulty outputs. The effectiveness, efficiency, and contribution of this approach to system performance were demonstrated by experiments. Tests carried out using different speech-text datasets and LSTM models yielded an average performance increase of 2.25%. With some advanced models, this ratio rises to 3.84%.

show abstract

“…Bir diğer yakın tarihli proje ise OrienTel projesidir. Bu proje Türkçe telefon konuşma veri tabanının tasarımını içermektedir [14]. Diğer bir veri kümesi ise Boğaziçi Üniversitesi'nin oluşturduğu Türkçe haber yayınlarından elde edilen konuşma veri kümesidir [15].…”

Section: Tablo 1 Konuşma Tanıma Teknolojisinin Kullanıldığı Alanlar unclassified

Otomatik Konuşma Tanımaya Genel Bakış, Yaklaşımlar ve Zorluklar: Türkçe Konuşma Tanımanın Gelecekteki Yolu

Oyucu

Sever

Polat

2019

Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım Ve Teknoloji

View full text Add to dashboard Cite

Figure A shows the application area of the Applications Automatic Speech Recognition (ASR) system. Adaptation is required for adaptation processes to be carried out according to the Application area. During the Speech Processing phase, which is the first entry point of the ASR system, feature extraction is performed from the audio signal. Individual properties are obtained by different feature extraction techniques. For example, Mel Frequency Cepstral Coefficient (MFCC) is a feature extraction technique commonly used in speech recognition systems. Decoder, one of the other components of ASR, converts the feature vectors obtained by using Acoustic Model (AM) and Language Model (LM) into phoneme sequences. In acoustic modeling, firstly, the posterior probability of the phoneme within a given time signal is calculated. In the artificial neural network-based acoustic model, the posterior probability of phonemes is independent for each window. This independence means that the phonemes in a word are independent of each other. Figure A. Basic architecture of speech recognition system.Purpose: This study presents a literature review on speech recognition and then discusses the recorded signs of progress made in this area of research for different languages. The data sets used in speech recognition systems, feature extraction approaches, speech recognition methods and performance evaluation criteria are examined and the focus is on the development of speech recognition and the difficulties in this field. Theory and Methods:In this study, literature review (systematic), which is an important component for a scientific article, was carried out. This process was carried out by the combination of different methods. A combination of review approaches is given.Results: According to the information obtained as a result of the research; Computational architectures that can be applied to resistance to the acoustic environment, self-learning in ASR, detection of unknown words, the success of the Turkish ASR at a broad and limited repertoire level, insufficient source status and Automatic Speech Recognition ASR were evaluated. In addition, the future of Turkish ASR was discussed and recommendations were made to overcome the current difficulties for Turkish ASR. Conclusion:The aim of this study is to examine the current speech recognition methods and approaches and to present the developments in this field in detail. For this reason, approaches, datasets and the difficulties faced by the researchers in their studies in this field are discussed in the scope of the study. The effect of deep learning and classical approaches on ASR was investigated. A road map is provided for researchers to incorporate the detailed information necessary for their work in this field to their own work and to overcome the present challenges.

show abstract

Turkish speech corpora and recognition tools developed by porting SONIC: Towards multilingual speech recognition

Cited by 27 publications

References 7 publications

Automatic recognition of oral vowels in tone language: Experiments with fuzzy logic and neural network models

Automatic recognition of oral vowels in tone language: Experiments with fuzzy logic and neural network models

Development of Output Correction Methodology for Long Short Term Memory-Based Speech Recognition

Otomatik Konuşma Tanımaya Genel Bakış, Yaklaşımlar ve Zorluklar: Türkçe Konuşma Tanımanın Gelecekteki Yolu

Contact Info

Product

Resources

About