Human-Robot Interface Using System Request Utterance Detection Based on Acoustic Features

Takiguchi, Tetsuya; Sako, A.; Revaud, J.; Yamagata, Tomoyuki; Miyake, Noriko; Ariki, Yasuo

doi:10.1109/mue.2008.87

Cited by 9 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For speaker dependent, when we compare points [5] with the same level of 80% average accuracy, then the low cost is used in the TSR algorithm without special hardware. For speaker independent, when we compare points [6] and [7], that are not supported at the same level of 68% average accuracy, then they display very high costs, as a result of using special hardware. That means that the speech commands are independent for any user, and in return can offer great benefits for general use in practical applications.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…This includes the implementation of the 'Ella Voice technique', which is a technique based upon speaker independence using 'cross-words techniques' that create a template reference, or concentrate upon detecting the 'end of a word'. Speech recognition based upon speaker independence and the 'hands-free technique', for human-robots, was proposed in the 'International Journal of Hybrid Information Technology' [6]. The recognition rate was measured at 89.93%.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Controlling Robots Using Thai Speech Recognition

Phanprasit

2014

AMR

View full text Add to dashboard Cite

Maximum security is essential for a robotic device to achieve its optimum control. In this research, we present robotic motions, controlled by technological speech recognition techniques, using commands of Thai Speech Recognition (TSR). Examples of such speech words used are; Sai, Khwa, Na, Lang Khun, Long and Yood, which are the equivalent English language representations for; turn left, turn right, forwards, backwards, upwards, downwards, and stop, respectively. The speech commands are independent for any particular user and so, as a result, they are highly beneficial for general and practical use. The three main important parts of this paper comprise; Pre-processing, Discrete Fourier Transform (DFT), and Back Propagation Neural Network (BPN). The experimental results, when reviewed, exhibit results showing that the average accuracy percentages are equal to 71.00% for female commands, and 70.00% for male commands, respectively.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

mentioning

confidence: 99%

Controlling Robots Using Thai Speech Recognition

Phanprasit

2014

AMR

View full text Add to dashboard Cite

show abstract

“…Benda yang dapat dideteksi oleh sensor PIR ini biasanya tubuh manusia [6]. Sensor f ngerprint adalah suatu sistem identifikasi terhadap seseorang melalui sidik jari [7]. Sistem ini berfungsi sebagai pengenal identitas sidik jari manusia, kemudian diterjemahkan menjadi suatu data yang dimengerti komputer [8].…”

Section: Pendahuluanunclassified

“…Sidik jari yang dikenali dapat dijadikan sebagai hasil akhir untuk sebuah aplikasi, seperti command and control, pemasukan data, dan persiapan dokumen. Parameter terbandingkan merupakan tingkat keakuratan sidik jari yang kemudian dicocokkan dengan template database yang tersedia [7], [9], [10]. Sensor fngerprint perlu kompleksitas algoritma yang diimplementasikan lebih sederhana dari sensor lainnya [8], [10], [11].…”

Section: Pendahuluanunclassified

See 1 more Smart Citation

Modul Elektronika Berbasis Mikrokontroler sebagai Sistem Pengaman pada Mobil Terintegrasi dengan Engine Immobilizer

Goeritno¹,

Afandi²

2019

JRE

View full text Add to dashboard Cite

An electronic module based on the ATmega32 microcontroller as a security system for cars that integrated into the engine immobilizer has been created. Three main things in this study, namely programming and verification tests, making an initial security system with a minimalist structure, and validation tests. Programming for the microcontroller system through algorithm determination and syntax writing, while the verification test is done through uploading the program syntax to the Proteus application and implementing the simulation. Determining the algorithms and writing the syntax through a number of steps, namely pin configuration, variable declarations, constant declarations, initialization, main programs, retrieve and send data, and output. The simulation assisted by the Proteus application is in the form of giving two kinds of commands/inputs to the sensor, namely one input data in the form of human existence or human motion to the passive infrared receiver sensor and one input of human fingerprint initialization data to the fingerprint sensor. The simulation results according to the order of the fingerprint sensor and passive infrared receiver in the form of a display on the Virtual Terminal. The minimalist structure of the system is composed of circuit diagrams, physical forms, and integrated wiring on the ATmega32 microcontroller system. The performance of the security system is shown, that the results of monitoring when the sensor is given input "human existence (motion)", the fingerprint sensor blinks (on) and when the fingerprint sensor blinks which means ready to receive input data in the form of "Human Initialization (fingerprint)" for activating actuators and starter system on the car. Giving input commands to the sensor passive infrared receiver and fingerprint has functioned for the appointment of performance, that the initial security system has been integrated with the main security systemand attached to the car.

show abstract