Ricoh Company, Ltd.

Nec Corporation

Mitsubishi Denki Kabushiki Kaisha

Kokusai Denshin Denwa Kabushiki Kaisha

Fuji Electric Co., Ltd.

Hitachi, Ltd.

Mitsubishi Electric Corporation

Sony Corporation

Renesas Electronics Corporation

Nintendo Co., Ltd.

Asahi Kasei Kabushiki Kaisha

Hitachi Industrial Products, Ltd.

Minipilo Electric Co., Ltd.

Hitoshi Yamamoto

Mutsuki Morinaga

Tadashi Kasai

Makoto Yasuda

Emiko Shiraishi

Takafumi Koshinaka

Takamasa Ozeki

Kunio Hasegawa

Masahiro Mizuno

Jun Hitosugi

Hiroshi Baba

Wakana Itoh

Yoshihiro Ejiri

Takatsugu Komori

Shiro Ogura

Hiromasa Kusakabe

Toshio Matsumoto

Kazuhiko Ito

Yuichi Aizawa

Makoto Nunokawa

Yoshihiko Yamazaki

Akira Ogawa

Kahei Furusawa

Kiyokazu Miki

Masahiko Shakuto

Kazuaki Kamihara

Shin Nishimura

Makoto Morishima

Tetsuya Muto

Koji Okabe

Takefumi Okumura

Kazuo Ito

Taiichiro Nakai

Kikuo Kawasaki

Shuji Komeiji

Kazuhiko Itoh

Shigeru Miyake

Masanori Sato

Norikazu Ueyama

Kazuhito Akiyama

Koichi Tatekura

Akira Satou

Keiko Kajimura

Ling Guo

Takayuki Suzuki

Hiroshi Nakai

Satoshi Nishiumi

Kazumi Kobayashi

Masato Iio

Hiroyuki Kunii

Toshikazu Kato

Masayoshi Nakayama

Hiroharu Wakabayashi

Yoshinao Iwamoto

Kohei Matsumoto

Masaki Sukesako

Ken Hanazawa

Yukio Nakagome

Yuuichiroh Uematsu

Tomohide Takenaka

Keita Sone

Tetsuya Yoshida

Kiyofumi Mochizuki

Ryo Okabe

Yasuhiko Niiro

Toyofumi Takahashi

Masakazu Terao

Masato Yamada

Tomoya Ohsugi

Takuma Higa

Masahiro Otake

Yasuhiro Izawa

Hiroki Konaka

Kazuyuki Yamaguchi

Keita Gotoh

Shinichi Ochiai

Kenji Komito

Kitsutaro Amano

Ryoji Yoshida

Kenji Asanuma

Ippei Kameda

Yasuhiro Tawara

Yoshinori Namihira

Tomomi Sano

Masaya Kurita

Masahiro Katoh

Akio Idehara

Naoki Taniguchi

Hitoshi Kadoya

Masanori Fukuhara

Mitsushige Baba

Sadahiro Yanai

Taiju Katayama

Shichao Peng

Kaoru Koida

Takuma Ueno

Jun Yabuki

A speech recognition apparatus () acquires source data () representing an audio signal including an utterance. The speech recognition apparatus () converts the source data () into a text string (). The speech recognition apparatus () generates a concatenated text () representing a content of an utterance by concatenating a text () included in the text string (). Herein, texts () adjacent to each other in the text string () are such that parts of associated audio signals overlap each other on a time axis. At a time of concatenating texts () adjacent to each other, the speech recognition apparatus () eliminates a trailing portion of a preceding text () and a leading portion of a succeeding text ().

Speech recognition apparatus, control method, and non-transitory storage medium

A speech recognition apparatus () includes a first model () and a second model (). The first model () is learned by training data with an audio frame as input data, and with, as correct answer data, compressed character string data acquired by encoding character string data represented by the audio frame. The second model () is a learned decoder () acquired by learning an autoencoder () being constituted of an encoder () converting input character string data into compressed character string data, and the decoder () converting, into character string data, the compressed character string data output from the encoder. The speech recognition apparatus () inputs an audio frame to the first model (), inputs, to the second model (), compressed character string data output from the first model (), and thereby generates character string data corresponding to the audio frame.

A block copolymer comprising wherein each curved portion represents a saturated or unsaturated hydrocarbon group having 1 to 20 carbon atoms which is unsubstituted or optionally has a substituent, X represents a group 1 element, and 'polymer' represents a polymer moiety.

Block copolymer, polymer composition, composition for viscous adhesive, viscous adhesive composition, and coupling agent

A speech processing device includes: first segment means for dividing first speech into a plurality of first speech segments; second segment means for dividing second speech into a plurality of second speech segments; primary speaker recognition means for calculating scores indicating similarities between the plurality of first and second speech segments; threshold value calculation means for calculating a threshold value based on scores indicating similarities between the plurality of first speech segments; speaker clustering means for classifying each of the plurality of second speech segments into one or more clusters having a similarity higher than the similarity indicated by the threshold value; and secondary speaker recognition means for calculating a similarity between each of the one or more clusters and the first speech and determining based on a result of the calculation whether speech corresponding to the first speech is contained in any of the one or more clusters.

Speech processing device, speech processing method, and non-transitory computer readable medium storing program

An audio processing apparatusis apparatus for generating a training data in speaker recognition. The audio processing apparatusincludes a data acquisition unit configured to acquire an audio signal that is a source of the training data as sample data, a data generation unit configured to executes signal processing on the acquired sample data, and to generates a new audio signal as the training data whose similarity with the sample data is within the set range.

Audio processing apparatus, audio processing method, and computer-readable recording medium

An authentication device is provided with: a plurality of attribute-dependent score calculation units each calculating an attribute-dependent score dependent on a prescribed attribute for input data; an attribute-independent score calculation unit for calculating an attribute-independent score independent of the attribute for the input data; an attribute estimation unit for performing attribute estimation for the input data; and a score integration unit for determining a score weight of each of a plurality of attribute-dependent scores and of the attribute-independent score using the result of the attribute estimation and calculating an output score using the attribute-dependent scores, the attribute-independent score, and the determined score weights.

Authentication device and authentication method

A neural network input unitinputs a neural network in which a first network having a layer for inputting an anchor signal belonging to a predetermined class and a mixed signal including a target signal belonging to the class and a layer for outputting, as an estimation result, a reconstruction mask indicating a time-frequency domain in which the target signal is present in the mixed signal, and a second network having a layer for inputting the target signal extracted by applying the mixed signal to the reconstruction mask and a layer for outputting a result obtained by classifying the input target signal into a predetermined class are combined. A reconstruction mask estimation unitapplies the anchor signal and mixed signal to the first network to estimate the reconstruction mask of the class to which the anchor signal belongs. A signal classification unitapplies the mixed signal to the estimated reconstruction mask to extract the target signal, and applies the extracted target signal to the second network to classify the target signal into the class.

Signal extraction system, signal extraction learning method, and signal extraction learning program

This speech processing device is provided with: a contribution degree estimation means which calculates a contribution degree representing a quality of a segment of the speech signal; and a speaker feature calculation means which calculates a feature from the speech signal, for recognizing attribute information of the speech signal, using the contribution degree as a weight of the segment of the speech signal.

Speaker recognition based on signal segments weighted by quality

A storage device () stores a failure correspondence table () that indicates a countermeasure for a time when a failure occurs in an apparatus mounted on a vehicle (). A failure countermeasure update unit () updates the countermeasure indicated in the failure correspondence table () in accordance with a change in a traveling environment of the vehicle ().

In-vehicle device, information processing method, and computer readable medium

The information processing apparatus () computes a first score representing a degree of similarity between the input sound data () and the registrant sound data () of the registrant (). The information processing apparatus () obtains a plurality of pieces of segmented sound data () by segmenting the input sound data () in the time direction. The information processing apparatus () computes, for each piece of segmented sound data piece (), a second score representing the degree of similarity between the segmented sound data () and the registrant sound data (). The information processing apparatusmakes first determination to determine whether a number of speakers of sound included in the input sound data () is one or multiple, using at least the second score. The information processing apparatus () makes second determination to determine whether the input sound data () includes the sound of the registrant (), based on the first score, the second scores, and a result of the first determination.

Information processing apparatus, control method, and program

An interrupt handler unit () generates a timer interrupt at an interrupt time, and executes an interrupt preparation process. A wait time period measurement unit () a measures a time period from completion of the interrupt preparation process to generation of a start request () as a wait time period. A time calculation unit () calculates a subtraction time period based on the wait time period measured by the wait time period measurement unit (), and calculates a preparation time period that is the sum of a time period obtained by subtracting the subtraction time period from the wait time period and a processing time period of the interrupt preparation process. The time calculation unit () stores a time obtained by shifting back the preparation time period from the time of a next start request (), as a next interrupt time, in a time storage unit ().

Interrupt control apparatus, interrupt control method, and computer readable medium

Leakage of a working fluid from a shaft sealing device of a turbomachine which handles a liquid as the working liquid is reduced and also unstable fluid force which acts on a rotor is reduced. For this purpose, the turbomachine has a rotor having an impeller, a bearing which rotatably supports the rotor, a casing which contains the rotor therein and forms a stationary flow passage, and the shaft sealing device which reduces the leakage of the working fluid through a gap part between the casing and the rotor. The working fluid is a liquid. A plurality of axial grooves which are intermittently arranged in axial direction and circumferential direction of the rotor with a land part being interposed are provided in an inner circumferential surface of the shaft sealing device.

Turbomachine

A speech processing apparatus, method and non-transitory computer-readable storage medium are disclosed. A speech processing apparatus may include a memory storing instructions, and at least one processor configured to process the instructions to calculate an acoustic diversity degree value representing a degree of variation in types of sounds included in a speech signal representing a speech, on a basis of the speech signal, and compensate for a recognition feature value calculated to recognize specific attribute information from the speech signal, using the acoustic diversity degree value.

Speech processing apparatus, speech processing method and computer-readable medium

Growing community of inventors

Tokyo, Japan

Hitoshi Yamamoto