Disambiguation in Unknown Object Detection by Integrating Image and Speech Recognition Confidences

Ozasa, Yuko; Ariki, Yasuo; Nakano, Mikio; Iwahashi, Naoto

doi:10.1007/978-3-642-37331-2_7

Cited by 6 publications

(10 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it cannot learn unknown objects although the method can discriminate the unknown objects from several objects. Nishimura et al dealt with the same task as [2], and they proposed a method for learning unknown objects that integrates information of speech and Web images [3]. It makes it possible to learn and recognize the object specified by speech even if there is one unknown object on a table.…”

Section: Related Workmentioning

confidence: 98%

“…Araki et al presented a robot that can learn the concept of an object via spoken dialog [7]. Ozasa et al proposed a method for object recognition using multimodal information in order to learn unknown objects in the object manipulation task where a human asks a robot via voice to bring an object among several objects on a table [2]. It can recognize the object only when the object specified by speech is known.…”

Section: Related Workmentioning

confidence: 99%

“…In order to bring the object, the robot must find and recognize the object using multimodal information of speech of the object name and images of the object. Several researchers have studied learning objects through interaction by multimodal information so that robots can recognize the object [2], [3], [6], [7]. In [6], they proposed a language acquisition model using speech and image information.…”

Section: Related Workmentioning

confidence: 99%

“…Several researchers have studied leaning objects through interaction. Ozasa et al [2] have proposed a method for object recognition using integrated information in order to learn unknown objects through the object manipulation task where a human makes a robot bring an object using his/her voice. In this paper, we aim at the same purpose and deal with the same task as shown in Fig.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Selection of Unknown Objects Specified by Speech Using Models Constructed from Web Images

Nishimura

Ozasa

Ariki

et al. 2014

2014 22nd International Conference on Pattern Recognition

Self Cite

View full text Add to dashboard Cite

To select an object requested by human voice among several unknown objects is one of the important tasks for household robots that assist human's daily lives. In this paper, we propose a method that can achieve this task. Using image models which are constructed by Web images collected from the results of speech recognition, the proposed method enables a robot to select an object specified by a speech from several unknown objects in a real environment.

show abstract

Section: Related Workmentioning

confidence: 98%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Selection of Unknown Objects Specified by Speech Using Models Constructed from Web Images

Nishimura

Ozasa

Ariki

et al. 2014

2014 22nd International Conference on Pattern Recognition

Self Cite

View full text Add to dashboard Cite

show abstract

“…The robot needs to learn objects in a home environment in order to interact in communication with humans. Several researchers have studied leaning objects through interaction [2], [3], [4], [5], [6]. Ozasa et al [6] have proposed the method for object recognition using integrated information in order to learn unknown objects through the object manipulation task that human makes a robot bring an object by human voice.…”

Section: Introduction and Related Workmentioning

confidence: 99%

Object Recognition by Integrated Information Using Web Images

Nishimura

Ozasa

Ariki

et al. 2013

2013 2nd IAPR Asian Conference on Pattern Recognition

Self Cite

View full text Add to dashboard Cite

It is an important task for a robot to bring objects requested by human via voice. In order to achieve the task, object recognition using speech and images is needed. Ozasa et al. has proposed the method for the object recognition by integrating speech and image information. Although this method requires both speech (word) and image models, the speech models are automatically constructed by combining phonemic acoustic models according to the dictionary. However, the image models have to be constructed manually in advance. In this paper, instead of the manual construction of the image models, we propose an automatic image model construction method for object recognition using Web images. The effectiveness of the proposed method is verified in the object recognition by integrating speech and image information.

show abstract