Abstract: To provide a data process unit and data process unit control program that are suitable for generating acoustic models for unspecified speakers taking distribution of diversifying feature parameters into consideration under such specific conditions as the type of speaker, speech lexicons, speech styles, and speech environment and that are suitable for providing acoustic models intended for unspecified speakers and adapted to speech of a specific person. The data process unit comprises a data classification section, data storing section, pattern model generating section, data control section, mathematical distance calculating section, pattern model converting section, pattern model display section, region dividing section, division changing section, region selecting section, and specific pattern model generating section.

Abstract: A microphone is installed on a surface of the skin immediately below the mastoid of a human to implement a sound sampling method including sampling at least one of a non-audible murmur, a whisper, or an audible sound. The microphone includes a condenser microphone portion having a pair of diaphragm electrodes and a contact portion which has an acoustic impedance close to the acoustic impedance of soft tissues in a body of a speaker, which is stuck tightly to the condenser microphone portion with no intervening air space, and which conducts an input speech from a skin surface of the speaker to the condenser microphone.

Abstract: When non-audible murmurs are to be obtained with maximum possible fidelity, the attenuation of the high frequency region attributable to mismatching of acoustic impedance on the interface between the skin surface over soft tissues in the body, which are mainly liquid, and the air space, which is gaseous, is restrained. The attenuation of the high frequency region attributable to mismatching of acoustic impedance can be restrained by installing a microphone on a surface of the skin immediately below the mastoid of a human, and sampling with condenser microphone portion via hardened silicone rubber or the like muscle-conduced vibrations of non-audible respiratory sounds articulated along with motions (motions of the mouth) not involving regular vibrations of the vocal cords.

Abstract: To provide a data process unit and data process unit control program that are suitable for generating acoustic models for unspecified speakers taking distribution of diversifying feature parameters into consideration under such specific conditions as the type of speaker, speech lexicons, speech styles, and speech environment and that are suitable for providing acoustic models intended for unspecified speakers and adapted to speech of a specific person. The data process unit comprises a data classification section, data storing section, pattern model generating section, data control section, mathematical distance calculating section, pattern model converting section, pattern model display section, region dividing section, division changing section, region selecting section, and specific pattern model generating section.

Abstract: To provide a data process unit and data process unit control program which are suitable for generating acoustic models for unspecified speakers taking distribution of diversifying feature parameters into consideration under such specific conditions as the type of speaker, speech lexicons, speech styles, and speech environment and which are suitable for providing acoustic models intended for unspecified speakers and adapted to speech of a specific person. A data process unit 1 comprises a data classification section 1a, data storing section 1b, pattern model generating section 1c, data control section 1d, mathematical distance calculating section 1e, pattern model converting section 1f, pattern model display section 1g, region dividing section 1h, division changing section 1i, region selecting section 1j, and specific pattern model generating section 1k.

Abstract: A speech processing apparatus which, in the process of performing echo canceling by using a pseudo acoustic echo signal, continuously uses an impulse response used for the previous frame as an impulse response to generate the pseudo acoustic echo signal when a voice is contained in the microphone input signal, and which uses a newly updated impulse response when a voice is not contained in the microphone input signal.

Abstract: Provided are an information recognition device, an information recognition method, and an information recognition program capable of recognizing predetermined information associated with an object-to-be-detected according to output of thermal radiation detection means for an object-to-be-detected existing in a detection range and a behavior pattern model corresponding to the output of the thermal radiation sensor corresponding to behavior patterns of objects prepared in advance by using a predetermined modeling method. The information recognition device 1 includes an infrared detection unit 10, a behavior pattern model generation unit 11, a behavior pattern model storage unit 12, and a recognition unit 13. The infrared detection unit 10 has a pyroelectric infrared sensor 10a and a signal processor 10b. The behavior pattern model generated is correlated to the behavior content and the attribute information and stored in the behavior pattern model storage unit 12.

Abstract: The present invention eliminates the disadvantages of an analysis target used by a cellular phone and speech recognition, that is, a normal sound which is transmitted through the air and which is externally sampled through a microphone, and improves the disadvantages that noise may be mixed or occur in the target, that information may leak, and that corrections are difficult. The present invention also provides a personal portable information terminal realizing new portable terminal communications which do not require training and which conform to the cultural practice of human beings. In the present invention, no apparatus that obtains an analysis target is put off human body, and a normal sound is not an analysis target. A stethoscope-type microphone is installed on the surface of the human skin.

Abstract: To provide a data process unit and data process unit control program which are suitable for generating acoustic models for unspecified speakers taking distribution of diversifying feature parameters into consideration under such specific conditions as the type of speaker, speech lexicons, speech styles, and speech environment and which are suitable for providing acoustic models intended for unspecified speakers and adapted to speech of a specific person. A data process unit 1 comprises a data classification section 1a, data storing section 1b, pattern model generating section 1c, data control section 1d, mathematical distance calculating section 1e, pattern model converting section 1f, pattern model display section 1g, region dividing section 1h, division changing section 1i, region selecting section 1j, and specific pattern model generating section 1k.

Abstract: The generic word label series used for recognition of words uttered by unspecified speakers are stored in the vocabulary label network accumulation processing. The speech of a particular speaker is entered. Based on the input speech, the registered word label series extraction processing generates the registered word label series. The registered word label series of the particular speaker can then be registered with the vocabulary label network accumulation processing.

Abstract: The generic word label series used for recognition of words uttered by unspecified speakers are stored in the vocabulary label network accumulation means f. The speech of a particular speaker is entered. Based on the input speech, the registered word label series extraction means d generates the registered word label series. The registered word label series of the particular speaker can then be registered with the vocabulary label network accumulation means f.