A new database for Turkish speech recognition on mobile devices and initial speech recognition results using the database

Büyük, Osman

doi:10.5505/pajes.2016.43765

Cited by 3 publications

(7 citation statements)

References 4 publications

(4 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, we perform experiments on 6.1 hours of Turkish recorded speech, these speeches were recorded using telephones (smartphones) for Turkish speech recognition purpose (database explained in [22] and summarized in Table 2). This speech database contains 549 speakers including males and females.…”

Section: Dataset/corpusmentioning

confidence: 99%

“…The audio was recorded from mobile platform using pulse code modulation with mono channel and sampled at 16 kHz, 16 bit. For language modelling (LM) a collection of 396k Turkish sentences obtained from the internet were used to build our unigram and bi-gram language model [22].…”

Section: Dataset/corpusmentioning

confidence: 99%

“…We will denote our system trained with deep neural network with the abbreviation DNN-HMM and the traditional Gaussian Mixture model will be abbreviated as GMM-HMM. In this paper, we illustrate the procedures and the steps involved to develop DNN-HMM and analyze how different choices in the design can exert influence on the recognition power, and we clearly show that DNN-HMM can be more profitable than the traditionally-trained GMM-HMM baseline on our mobile recorded dataset [22].…”

Section: Introductionmentioning

confidence: 96%

“…For this purpose, we constructed a Turkish speech database which consists of recordings from mobile smart phones since there is no publicly available database for the task. We chose the mobile SR domain since it is an emerging application field [22]. In the future, we plan to distribute the database for academic research purpose.…”

Section: Introductionmentioning

confidence: 99%

“…In this paper, we propose a hybrid setup of deep neural network (DNN) and Hidden Markov model (HMM) on a subset of Turkish speech dataset [22]. The neural network is trained using 6.1hours of Turkish speech obtained by mobile-recordings of 549 Turkish native speakers.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Turkish Speech Recognition Based On Deep Neural Networks

Kimanuka¹,

Büyük²

2018

SDÜ Fen Bil Enst Der

Self Cite

View full text Add to dashboard Cite

In this paper we develop a Turkish speech recognition (SR) system using deep neural networks and compare it with the previous state-of-the-art traditional Gaussian mixture model-hidden Markov model (GMM-HMM) method using the same Turkish speech dataset and the same large vocabulary Turkish corpus. Nowadays most SR systems deployed worldwide and particularly in Turkey use Hidden Markov Models to deal with the speech temporal variations. Gaussian mixture models are used to estimate the amount at which each state of each HMM fits a short frame of coefficients which is the representation of an acoustic input. A deep neural network consisting of feed-forward neural network is another way to estimate the fit; this neural network takes as input several frames of coefficients and gives as output posterior probabilities over HMM states. It has been shown that the use of deep neural networks can outperform the traditional GMM-HMM in other languages such as English and German. The fact that Turkish language is an agglutinative language and the lack of a huge amount of speech data complicate the design of a performant SR system. By making use of deep neural networks we will obviously improve the performance but still we will not achieve better result than English language due to the difference in the availability of speech data. We present various architectural and training techniques for the Turkish DNN-based models. The models are tested using a Turkish database collected from mobile devices. In the experiments, we observe that the Turkish DNN-HMM system have decreased the word error rate approximately 2.5% when compared to the GMM-HMM traditional system.

show abstract

Section: Dataset/corpusmentioning

confidence: 99%

Section: Dataset/corpusmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 96%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Turkish Speech Recognition Based On Deep Neural Networks

Kimanuka¹,

Büyük²

2018

SDÜ Fen Bil Enst Der

Self Cite

View full text Add to dashboard Cite

show abstract

Development of Intelligent Companion Robot for Hospitals

Kok

Guduk

Gengec

et al. 2020

2020 Innovations in Intelligent Systems and Applications Conference (ASYU)

View full text Add to dashboard Cite

Deep Learning Based Automatic Speech Recognition for Turkish

Tombaloğlu¹,

Erdem

2020

Sakarya University Journal of Science

View full text Add to dashboard Cite

Using Deep Neural Networks (DNN) as an advanced Artificial Neural Networks (ANN) has become widespread with the development of computer technology. Although DNN has been applied for solving Automatic Speech Recognition (ASR) problem in some languages, DNNbased Turkish Speech Recognition has not been studied extensively. Turkish language is an agglutinative and a phoneme-based language. In this study, a Deep Belief Network (DBN) based Turkish phoneme and speech recognizer is developed. The proposed system recognizes words in the system vocabulary and phoneme components of out of vocabulary (OOV) words. Sub-word (morpheme) based language modelling is implemented into the system. Each phoneme of Turkish language is also modelled as a sub-word in the model. Sub-word (morpheme) based language model is widely used for agglutinative languages to prevent excessive vocabulary size. The performance of the suggested DBN based ASR system is compared with the conventional recognition method, GMM (Gaussian Mixture Method) based Hidden Markov Model (HMM). Regarding to performance metrics, the recognition rate of Turkish language is improved in compare with previous studies.

show abstract

A new database for Turkish speech recognition on mobile devices and initial speech recognition results using the database

Cited by 3 publications

References 4 publications

Turkish Speech Recognition Based On Deep Neural Networks

Turkish Speech Recognition Based On Deep Neural Networks

Development of Intelligent Companion Robot for Hospitals

Deep Learning Based Automatic Speech Recognition for Turkish

Contact Info

Product

Resources

About