Nec Corporation

Nec Platforms, Ltd.

Other

Nec C Orporation

Takafumi Koshinaka

Takayuki Arakawa

Hitoshi Yamamoto

Qiongqiong Wang

Koji Okabe

Masahiro Tani

Masahiro Saikou

Yoshifumi Onishi

Makoto Terao

Kouji Oosugi

Kong Aik Lee

Tasuku Kitade

Kohei Osugi

Ryoma Oami

Hiroyoshi Miyano

Osamu Houshuyama

Ling Guo

Takayuki Suzuki

Shinichi Ando

Hitoshi Imaoka

Masahiko Hamanaka

Shuji Komeiji

Shigeru Sawada

Hideki Irisawa

Shouhei Yano

Kaoru Koida

The voice registration deviceX mainly includes a noise reproduction meansX, a voice data acquisition meansX, and a voice registration meansX. The noise reproduction meansX is configured to reproduce noise data during a time period in which voice input from a user is performed. The voice data acquisition meansX is configured to acquire the voice data based on the voice input. The voice registration meansX is configured to register the voice data or data generated based on the voice data as data to be used for verification relating to a voice of the user.

Voice registration device, control method, program, and storage medium

A speech enhancement meansdetermines an enhancement mask generated based on a mask for speech enhancement, when a test utterance is input as speech data. A first hyper-parameter optimization meansdetermines, when the test utterance is input, a first hyper-parameter which is a hyper-parameter representing the degree to which the signal representing the test utterance is kept using the mask, and the first hyper-parameter which is set to take into account a downstream task that is processed using an enhanced test utterance. A mask generation meansgenerates an adaptive mask from the determined enhancement mask and the first hyper-parameter that enhances the test utterance for the downstream task. The mask generation meansgenerates the adaptive mask in which the first hyper-parameter is a power of the mask.

Hyper-parameter optimization system, method, and program

A spoofing detection apparatusincludes a multi-channel spectrogram creation unitand an evaluation unit. The multi-channel spectrogram creation unitextracts different type of spectrograms from speech data and integrates the different type of spectrograms to create a multi-channel spectrogram. The evaluation unitevaluates the created multi-channel spectrogram by applying the created multi-channel spectrogram to a classifier constructed using labeled multi-channel spectrograms as training data and classifies it to either genuine or spoof.

Neural network-based signal processing apparatus, neural network-based signal processing method, and computer-readable storage medium

Provided is to prevent a false determination due to an attachment condition of an apparatus that transmits and receives an acoustic signal, and perform accurate personal authentication. A personal authentication device includes: a personal authentication means that authenticates an individual by using first information at least including an acoustic characteristic calculated from an acoustic signal propagating through the head of the user, which is detected by an apparatus being attached on a head of a user for transmitting and receiving the acoustic signal, and a feature amount extracted from the acoustic characteristic; an attachment trouble rule storage means that stores an attachment trouble rule for detecting an attachment trouble with the apparatus; and an attachment trouble detection means that detects a trouble with an attachment state of the apparatus when the first information satisfies the attachment trouble rule.

Detection of attachment problem of apparatus being worn by user

Provided is a personal authentication device capable of simply securing security with little psychological and physical burden of a user to be authenticated. Personal authentication device includes: transmission unit that transmits a first acoustic signal to a user's head; observation unit that observes a second acoustic signal after the first acoustic signal propagation; calculation unit that calculates acoustic characteristics from the first and the second acoustic signal; extraction unit that extracts a feature amount related to a user from the acoustic characteristics; storage control unit that registers the feature amount in the storage unit; identification unit that identifies the user by collating the first feature amount with a second feature amount; and storage unit stores the first feature amount, wherein while identification unit identifies the user as being identical, transmission unit transmits the first acoustic signal every predetermined interval.

Personal authentication device based on echo sounds, personal authentication method, and recording medium

Provided is a personal authentication device capable of simply securing security with little psychological and physical burden of a user to be authenticated. Personal authentication device includes: storage that stores first and second identification information for identifying a user; analysis unit that analyzes information inputted to a user and generates the first identification information; transmission unit that transmits a first acoustic signal to a part of a user's head; observation unit that observes a second acoustic signal; calculation unit that calculates acoustic characteristics from the first and the second acoustic signal; extraction unit that extracts an acoustic feature amount from the acoustic characteristics as second identification information; and determination unit that determines the user to be identical when first identification information registered and the first identification information generated coincide with each other and second identification information registered and the second identification information extracted coincide with each other.

Acoustic personal authentication device, personal authentication method, and recording medium

Provided is a first acoustic information acquisition unit configured to acquire a first acoustic information obtained by receiving a sound wave emitted from a first sound source by a wearable device worn by a user, a second acoustic information acquisition unit configured to acquire a second acoustic information obtained by receiving a sound wave emitted from a second sound source that is different from the first sound source by the wearable device, and a third acoustic information acquisition unit configured to acquire a third acoustic information used for biometric matching of the user based on the first acoustic information and the second acoustic information.

Information processing device, wearable device, information processing method, and storage medium

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

Provided are a personal authentication device performing accurate authentication immediately follow insertion an earphone/microphone device to wear, and preventing spoofing after authentication. This device: detects contact of an earphone/microphone device with a propagation path constituting part of the head of a person; generates a first acoustical signal in an audible range upon detecting said contact; measures an acoustical signal resulting from propagation of the first acoustical signal; determines that first authentication of the person is successful if the measured propagated first acoustical signal satisfies predetermined conditions; generates a second acoustical signal in an inaudible range higher in frequency than said audible range; measures an acoustical signal resulting from propagation of the second acoustical signal; and performs second authentication in which, if the measured propagated second acoustical signal satisfies predetermined conditions, then it is determined that the person is the person to be authenticated, for whom the first authentication is successful.

Personal authentication device, personal authentication method, and recording medium

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.

Growing community of inventors

Tokyo, Japan

Takafumi Koshinaka