Kabushiki Kaisha Toshiba

Koji Ueno

Nobuhiro Shimogori

Tomoo Ikeda

Osamu Nishiyama

Hirokazu Suzuki

Kenta Cho

Manabu Nagao

Kouta Nakata

Taira Ashikawa

Akira Kumano

Shinichi Nagano

Keisuke Nishimura

Sogo Tsuboi

Kenta Sasaki

According to an embodiment, a text generator includes a recognizer, a selector, and a generation unit. The recognizer is configured to recognize an acquired sound and obtain recognized character strings in recognition units and confidence levels of the recognized character strings. The selector is configured to select at least one of the recognized character strings used for a transcribed sentence on the basis of at least one of a parameter about transcription accuracy and a parameter about a workload needed for transcription. The generation unit is configured to generate the transcribed sentence using the selected recognized character strings.

Text generator, text generating method, and computer program product

According to one embodiment, a speaker clustering apparatus includes a clustering unit, an extraction unit, and an error detection unit. The clustering unit is configured to extract acoustic features for speakers from an acoustic signal, and to cluster utterances included in the acoustic signal into the speakers by using the acoustic features. The extraction unit is configured to acquire character strings representing contents of the utterances, and to extract linguistic features of the speakers by using the character strings. The error detection unit is configured to decide that, when one of the character strings does not fit with a linguistic feature of a speaker into which an utterance of the one is clustered, the utterance is erroneously clustered by the clustering unit.

Apparatus and method for clustering speakers, and a non-transitory computer readable medium thereof

According to one embodiment, an information extracting method includes: collecting a text in which a keyword of interest appears, the keyword of interest, and a time of creation of the text; extracting a keyword included in the text except for the keyword of interest and configured to extract the time of creation; extracting the keyword having a time score obtained on the basis of an appearance frequency of the keyword in a time interval exceeding a first threshold value and a local score obtained from the appearance frequency of the keyword in a predetermined local area exceeding a second threshold value as a local hot word, and also extract the extracted time interval of the extracted keyword and the keyword of interest corresponding to the keyword; and storing the extracted local hot word, the time interval, and the keyword of interest.

Information extracting server, information extracting client, information extracting method, and information extracting program

An information processing apparatus is connected with at least one external apparatus via a network. An input image of a first user related to the information processing apparatus is accepted while displaying a plurality of target images on a display. The plurality of target images includes an image of a second user related to the external apparatus. A gaze of the first user is detected from the input image. A target image looked by the first user is recognized from the plurality of target images, based on the gaze. A first head model as a head model of the first user, and a first texture to be projected onto the first head model, are generated. A first ID to identify a subject of the target image, the first head model and the first texture, are transmitted to the external apparatus.

Information processing apparatus and network conference system

Growing community of inventors

Mishima, Japan

Koji Ueno