ABSTRACT
This paper presents a novel system that supports the specification and execution of conditional Web of Things (WoT) applications over voice. We illustrate the architecture of our system that consists of the key components such as a Cloud-based automatic speech recognition (ASR), an application composition engine and an event-based platform for application execution. We demonstrate this system through a mobile voice-based personal assistance application. Through this demonstration, we highlight our technical contributions that address the shortcomings of the existing voice-based applications and introduce further challenges.
- Apple Siri. http://www.apple.com/ios/siri/.Google Scholar
- ElasticSearch. http://www.elastic.co/.Google Scholar
- IFTTT. http://www.ifttt.com/.Google Scholar
- S Voice. http://www.androidcentral.com/tag/s-voice.Google Scholar
- SmartThings. http://www.smartthings.com.Google Scholar
- E. Fosler-Lussier, Y. He, P. Jyothi, and R. Prabhavalkar. Conditional random fields in speech, audio, and language processing. Proceedings of the IEEE, 101(5):1054--1075, May 2013.Google ScholarCross Ref
- A. Kiryakov, B. Popov, I. Terziev, D. Manov, and D. Ognyanoff. Semantic annotation, indexing, and retrieval. Web Semant., 2(1):49--79, Dec. 2004. Google ScholarDigital Library
- G. A. Miller. Wordnet: A lexical database for english. Commun. ACM, 38(11):39--41, Nov. 1995. Google ScholarDigital Library
- Y. Yoon, C. Ye, and H.-A. Jacobsen. A distributed framework for reliable and efficient service choreographies. In Proceedings of the 20th International Conference on World Wide Web, WWW '11, pages 785--794, New York, NY, USA, 2011. ACM. Google ScholarDigital Library
Index Terms
- A System for the Specification and Execution of Conditional WoT Applications over Voice
Recommendations
Towards the creation of reliable voice control system based on a fuzzy approach
Proposed enhancements of the FPD method increases the command recognition accuracy.Commands are extracted from continuous speech if vowels in a command are stressed.Isolated syllable mode improves the speech recognition quality for Russian language. The ...
A wavelet- and neural network-based voice interface system for wheelchair control
Voice control has long been considered as a natural mechanism to assist powered wheelchair users. However, one implementation difficulty is that a voice input system may fail to recognise a user's voice. Indeed, speech activated interface between human ...
Phonetic posteriorgram-based voice conversion system to improve speech intelligibility of dysarthric patients
Highlights- Proposed a dysarthria voice conversion system that can effectively improve dysarthria speech intelligibility.
Abstract Background and ObjectiveMost dysarthric patients encounter communication problems due to unintelligible speech. Currently, there are many voice-driven systems aimed at improving their speech intelligibility; however, the ...
Comments