Voice command recognition methods for smart houses

Öz

The smart home system allows the user to more easily control and monitor the lighting, security, ventilation, air conditioning etc. systems of a house. Today, many researchers and technology company are conducting studies on smart homes. One area of the studies is that smart homes can be managed with voice commands without the need for any control devices. From the 1950s to now, a lot of work has been done to manage a system with voice commands and many methods have been developed. In this study, the studies made in the field up to today and the algorithms, products, services etc. that emerged as the result of these studies are examined. It has been researched that which cases they can be used in order for a smart home system to work with voice commands and what are the advantages and disadvantages of them in which situation.

Anahtar Kelimeler

• Smart home,speech recognition,voice recognition

Akıllı evler için sesli komut algılama yöntemleri

Öz

Akıllı ev sistemi evin aydınlatma, güvenlik, havalandırma, sıcaklık vb. sistemlerinin kullanıcı tarafından daha kolay kontrol ve takip edilebilmesini sağlamaktadır. Günümüzde birçok araştırmacı ve teknoloji şirketi akıllı evler üzerine çalışmalar yürütmektedir. Çalışmaların bir alanı da akıllı evlerin sesli komutlar ile herhangi bir kumanda aletine gerek kalmadan yönetilebilmesidir. Sesli komutlar ile bir sistemin yönetilmesi için 1950’lerden başlayarak günümüze kadar birçok çalışma yapılmış ve yöntem geliştirilmiştir. Bu çalışmada da bugüne değin alanda yapılmış çalışmalar ve çalışmalar sonucunda ortaya çıkmış algoritma, ürün, servis vb. incelenmiş, bunların bir akıllı ev sisteminin sesli komutlar ile çalışabilmesi için hangi durumlarda kullanılabileceği ve hangi durumlarda ne gibi avantaj ve dezavantajlara sahip olduğu araştırılmıştır.

Anahtar Kelimeler

• Akıllı ev,konuşma tanıma,ses tanıma

Kaynakça

1. Yılmaz, H., Akıllı ev’in dünyadaki ve Türkiye’deki yeri, Bina Elektrik, Elektronik, Mekanik ve Kontrol Sistemleri Dergisi, (2004).
2. McDonald, C.W., Talk to your house with these voice-activated smart-home systems, (2015). https://www.cnet.com/news/talk-to-your-house-with-these-voice-activated-smart-home-systems/, (14.08.2017).
3. Gelegin, İ. ve Bolat, B., Ayrık kelime tabanlı bir konuşma tanıma sistemiyle bilgisayar kontrolü, Elektrik-Elektronik ve Bilgisayar Sempozyumu, Elazığ, 2011.
4. Gürel, A. ve Arslan, L.M., Konuşma tanıma için insan-makine karşılaştırması, Dilbilim Araştırmaları, (2008).
5. Yusnita, M.A., Paulraj, M.P., Yaacob, S., Abu Bakar, S., Saidatul, A., Abdullah, A.N., Phoneme-based or ısolated-word modeling speech recognition system? an overview, International Colloquium on Signal Processing and its Applications, Penang, (2011).
6. Rana, M. ve Saloni, E., A review on automatic speech recognition system, International Journal Of Engineering And Computer Science, 9849-9852, (2015).
7. Nugues, P., An overview of speech synthesis and recognition, Language Processing with Perl and Prolog, Springer, 1-3, (2014).
8. Jarande, S.S. ve Waghmare, S., A survey on different classifier in speech recognition techniques, International Journal of Emerging Technology and Advanced Engineering, 534-539, (2014).

9. Comparing Top Deep Learning Frameworks: Deeplearning4j, Torch, Theano, TensorFlow, Caffe, Paddle, MxNet, Keras & CNTK, (2017). https://deeplearning4j.org/compare-dl4j-torch7-pylearn.html#comparing-top-deep-learning-frameworks-deeplearning4j-torch-theano-tensorflow-caffe-paddle-mxnet-keras--cntk, (11.08.2017).
10. Top 5 Open Source Speech Recognition Toolkits, (2016). http://blog.neospeech.com/top-5-open-source-speech-recognition-toolkits/, (14.08.2017).
11. RSC-4X Family of Speech Recognition And Synthesis Microcontrollers, (2017). http://www.sensory.com/products/integrated-circuits/rsc-4x-series/, (14.08.2017).
12. HM2007, (2007). http://www.imagesco.com/speech/HM2007.pdf, (15.08.2017).
13. Speech Recognition Reference Design on the C5535 eZdsp(TM), (2016). http://www.ti.com/tool/tidep0066, (14.08.2017).
14. EasyVR Shield 3.0 - Voice Recognition Shield, (2017). https://www.sparkfun.com/products/13316, (14.08.2017).
15. The ES6929P - Stand Alone Speech Recognition For Arduino, (2015). https://www.kickstarter.com/projects/172204344/the-es6929p-stand-alone-speech-recognition-for-ard, (14.08.2017).
16. N. Shmyrev, What are the top ten speech recognition APIs?, (2016). https://www.quora.com/top-ten-speech-recognition-APIs, (14.08.2017).
17. R. Crist, Talk to your house with these voice-activated smart-home systems, (2015). https://www.cnet.com/news/talk-to-your-house-with-these-voice-activated-smart-home-systems/, (14.08.2017).
18. SpeechRecognition, (2017). https://pypi.python.org/pypi/SpeechRecognition/, (14.08.2017).
19. Internet Access, (2017). https://data.oecd.org/ict/internet-access.htm, (14.08.2017).
20. Open Speech and Language Resources, (2017). http://www.openslr.org/resources.php, (14.08.2017).
21. S. K. Gaikwad, B. W. Gawali ve P. Yannawar, A Review on Speech Recognition Technique, International Journal of Computer Applications, 16-24, (2010).
22. What is HTK?, (2016). http://htk.eng.cam.ac.uk/, (14.08.2017).
23. NVIDIA Jetson TX2: The New Gold Standard for AI at the Edge, (2017). https://news.developer.nvidia.com/introducing-the-nvidia-jetson-tx2-the-new-gold-standard-for-ai-at-the-edge/, (14.08.2017).
24. MOVI™ Arduino Shield, (2016). http://www.audeme.com/movi.html, (16.05.2017).
25. Integrate Dragon speech recognition into your applications, (2017). https://www.nuance.com/dragon/for-developers/dragon-software-developer-kit.html, (10.08.2017).
26. Cloud Speech Api, (2017). https://cloud.google.com/speech/, (14.08.2017).
27. Bing Speech Api, (2017). https://azure.microsoft.com/en-us/services/cognitive-services/speech/, (14.08.2017).
28. Smart Home, (2017). https://api.ai/, (14.08.2017).
29. Natural Language for Developers, (2017). https://wit.ai/, (25.05.2017).
30. Echo & Echo Dot, (2017). https://developer.amazon.com/echo, (22.08.2017).