Kabushiki Kaisha Toshiba

Tokyo Shibaura Denki Kabushiki Kaisha

Kensuke Uehara

Tsuneo Nitta

Sadakazu Watanabe

Yasuo Takahashi

Kunihiko Sekiya

Satoru Hashimoto

Hidenori Shinoda

Michiaki Okano

Tomio Sakata

Katsuhiko Kuma

Hirobumi Karasawa

Yoichi Takebayashi

Kazunori Iwasaki

Katsumi Nitta

Haruo Asada

Shouichi Hirai

A control unit transmits address area designation information designating an arbitrary bit position in ID data. At least a response unit transmits a response signal with an error detection code attached to predetermined information in the unique information held in itself by means of a time slot determined by the address area designation information and the ID data of the particular response unit. The control unit checks for the presence or absence of an error of the information in each time that has arrived, fetches only the response signal free of error, and transmits the error presence-absence information indicating the inspection result. Further, in the case where there exists a time slot having an error, the control unit transmits new address area designation information. In the case where an error exists in the time sot used previously by the response unit, the response unit retransmits the response signal in the time slot determined from the new address area designation information and the ID data of the response unit.

Information identification system for identifying response units by a

A voice-controlled device of this invention includes a receiving/discriminating mechanism for receiving a DTMF signal externally input through a telephone line and discriminating the DTMF signal, a level detecting mechanism for detecting a signal level of the DTMF signal input to the receiving/discriminating mechanism, a speech recognizer for recognizing the content of a voice signal externally input through the telephone line, an input level adjustor for adjusting a signal level of the voice signal input to the speech recognizer on the basis of the signal level detection result by the level detecting mechanism, and a function executor for executing a function according to the content of the voice signal recognized by the speech recognizer.

Voice-controlled apparatus using telephone and voice-control method

An apparatus and method for inputting a voice through a microphone mounted at a position facing a speaking person. An image of a speaking person is generated and used to detect the position of a mouth of the speaker. The microphone is then moved in accordance with position of the mouth.

Method and apparatus for inputting a voice through a microphone

Phoneme feature parameters are extracted from input digital speech signals by means of LPC analysis. Phonetic segments having phonetical meanings are obtained together with similarities to prescribed basic phonetic segments from the feature parameters to be passed through nodes of transition networks provided for each word. In passing the nodes, scores for similarity Sj of predetermined segments of the corresponding phonetic segments are made in selective scoring and the accumulation of the scores is used for recognition of continuous word speech.

System for continuous speech recognition through transition networks

In a speech recognition system for recognizing speeches uttered by non-specific speakers, start and end points of a word or speech interval are determined by a novel preprocessor for searching a sound power level to obtain speech boundary candidates and for determining likelihoods of speech or word intervals on the basis of the boundary candidates. Since likelihoods (probabilities) are determined for speech interval candidates, the similarity rate between feature parameters and reference pattern set of a speech signal are calculated for only the higher likelihood candidates, thus improving the accuracy and the speed of speech recognition. A percentage of erroneous boundary decision is about 0.5% when two speech interval candidates of the first and second likelihoods are adopted.

Speech recognition system

An acoustic signal processing circuit extracts input speech pattern data and subsidiary feature data from an input speech signal. The input speech pattern data comprise frequency spectra, whereas the subsidiary feature data comprise phoneme and acoustic features. These data are then stored in a data buffer memory. The similarity measures between the input speech pattern data stored in the data buffer memory and reference speech pattern data stored in a dictionary memory are computed by a similarity computation circuit. When the largest similarity measure exceeds a first threshold value and when the difference between the largest similarity measure and the second largest measure exceeds a second threshold value, category data of the reference pattern which gives the largest similarity measure is produced by a control circuit to correspond to an input speech. When recognition cannot be performed, the categories of the reference speech patterns which respectively give the largest to mth similarity measures are respectively compared with the subsidiary feature data. In this manner, subsidiary feature recognition of the input voice is performed by a subsidiary feature recognition section.

Growing community of inventors

Tokyo, Japan

Kensuke Uehara