Nec Corporation

Eiko Yamada

Hiroaki Hattori

Kazunaga Yoshida

Hiroshi Hagane

There are provided a mobile terminal capable of switching a function of the mobile terminal depending on whether a sensor is contacted or not contacted, a mobile terminal control method, a mobile terminal control program, and a recording medium. A mobile phoneincludes a touch sensorat a position where a user generally contacts the mobile phonewhen the user holds it. While a user is in contact with the touch sensor, the mobile phonecan perform normal operation. If the mobile phonecontinues to be not in contact with the touch sensorfor a certain time, it switches from the normal operation. For example, assume that a lock mode setting is made. The mobile phoneswitches to a lock mode while it is not in contact with the touch sensor. When the touch sensoris contacted again, the mobile phoneshifts to a state for unlock processing such as password entry. If an entry is normally made, the mobile phoneis unlocked.

Mobile terminal and method for controlling lock and unlock functions by means of contact sensor

A client () transmits a service request signal to a Web server (). The Web server which has received the service request signal generates an ID for each session, and transmits the ID to the client together with window information. The client then transmits input voice information to a voice processing server () together with the ID. The voice processing server which has received the voice information and the ID processes the voice information, and transmits the processing result to the Web server together with the ID. The Web server prepares information reflecting the voice processing result obtained by the voice processing server in correspondence with the ID from the voice processing server, and transmits the information to the client. Letting the client, Web server, and voice processing server share an ID for each session in this manner allows the server side to comprehend the relationship between the information downloaded from the Web server to the client and the voice information transmitted from the client to the voice processing server. As a consequence, even if the Web server and the voice processing server receive access from a plurality of clients, proper information reflecting the voice processing result can be downloaded.

Voice processing unit and system, and voice processing method

To provide a speech recognition apparatus which enables the reduction of transmission time and of costs. A terminal-side apparatus () includes a speech detection portion () for detecting a speech interval of inputted data, a waveform compression portion () for compressing waveform data at the detected speech interval, and a waveform transmission portion () for producing the compressed waveform data. A server-side apparatus () includes a waveform reception portion () for receiving the waveform data transmitted from the terminal-side apparatus, a waveform decompression portion () for decompressing the received waveform data, an analyzing portion () for analyzing the decompressed waveform data, and a recognizing portion () for performing recognition processing to produce a recognition result.

Server-client type speech recognition apparatus and method

A voice recognition system, method and storage medium is provided. The system includes a plurality of storage sections, a selection section, an adaptation section, a plurality of calculation sections, an adaptation section, a normalization section and a decision section. The method includes the steps for performing the functions associated with the sections.

Speech recognition apparatus, method and storage medium thereof

In a speaker recognition system, a tree-structured reference pattern storing unit has first through M-th node stages each of which has nodes that respectively store a reference pattern of inhibiting speakers. The reference pattern of each node of (N-1)-th node stage represents acoustic features in the reference patterns of predetermined ones of the nodes of the N-th node stage. An analysis unit analyzes input speech and converts the input speech into feature vectors. A similarities calculating unit calculates similarities between the feature vectors and the reference patterns of all of the inhibiting speakers. An inhibiting speaker selecting unit sorts the similarities and selects a predetermined number of inhibiting speakers. The similarities calculating unit calculates the similarity of the node of the first node stage and calculates the similarities of ones of the nodes of the N-th node stage which are connected to a predetermined number of nodes of the (N-1)-th node stage, selected in an order based on highest similarities.

Tree structured cohort selection for speaker recognition system

Speech data is converted into logarithmic spectrum data and orthogonally transformed to develop feature vectors. Normalization coefficient data and unit vector data are stored. An inner product of the feature vector data and the unit vector data is calculated. The inner product may be the average of inner products for a word or a sentence, or may be a regressive average of them. A normalization vector, which corresponds to a second or higher order curve obtained by least-square error approximation of the speech data on logarithmic spectrum space, is calculated on the transformed feature vector space by using the inner product, the normalization coefficient data, and the unit vector data. Normalization of the feature vectors is performed by subtracting the normalization vector from the feature vectors on the transformed feature vector space. Then, a recognition is performed based on the normalized feature vector.

Growing community of inventors

Tokyo, Japan

Eiko Yamada