Ntt Docomo, Inc.

Akira Hiraiwa

Toshiaki Sugimura

Hiroyuki Manabe

Toshio Miki

Hirotaka Nakano

Kouki Hayashi

Takashi Ninjouji

Yumiko Hiraiwa, Legal Representative

The object of the present invention is to keep a high success rate in recognition with a low-volume of sound signal, without being affected by noise. The speech recognition system comprises a sound signal processorconfigured to acquire a sound signal, and to calculate a sound signal parameter based on the acquired sound signal; an electromyographic signal processorconfigured to acquire potential changes on a surface of the object as an electromyographic signal, and to calculate an electromyographic signal parameter based on the acquired electromyographic signal; an image information processorconfigured to acquire image information by taking an image of the object, and to calculate an image information parameter based on the acquired image information; a speech recognizerconfigured to recognize a speech signal vocalized by the object, based on the sound signal parameter, the electromyographic signal parameter and the image information parameter; and a recognition result providerconfigured to provide a result recognized by the speech recognizer

Speech recognition system, speech recognition method, speech synthesis system, speech synthesis method, and program product

A speaking period required for a voice recognition processing is detected with a simple and robust approach. A speaking period is detected based on an EMG generated when a speaker speaks. A large amplitude is observed in an EMG as muscular activity is caused when a speaker speaks. By observing this, a speaking period can be detected. The EMG can be measured from the speaker's skin via electrodes provided on a mobile-type terminal. Since a mobile-type terminal is usually pressed to the skin for use, affinity between this use form and the present invention is very high.

Speaking period detection device, voice recognition processing device, transmission system, signal level control device and speaking period detection method

Information relating to an amount of muscle activity is extracted from a myo-electrical signal by activity amount information extraction means, and information recognition is performed by activity amount information recognition means using the information relating to the amount of muscle activity of a speaker. There is a prescribed correspondence relationship between the amount of muscle activity of a speaker and a phoneme uttered by a speaker, so the content of an utterance can be recognized with a high recognition rate by information recognition using information relating to an amount of muscle activity.

Information recognition device and information recognition method

A mobile terminal capable of measuring a biological signal is provided. The terminal comprises a terminal body; an electrode for human body earth or system reference, placed on an outer surface of the terminal body so as to be contactable with the skin of a user of the mobile terminal; and differential electrodes. The measured biological signals include an electromyography signal and an electroencephalogram signal. The differential electrodes can be external to the terminal body and be connected via lead lines to the terminal body.

Mobile terminal capable of measuring a biological signal

Speech recognition system, speech recognition method, speech synthesis system, speech synthesis method, and program product having increased accuracy

The myo-electric information of the user is transmitted to the data center, learning with a high computation load for generating recognition parameters required for recognizing the utterance content based on the myo-electric information is performed, not by the mobile communication terminal, but by the data center. By this, compared with the case when learning is performed in the mobile communication terminal which has stricter limitations on processing speed and memory than a stationary type computer, efficient learning in a shorter time becomes possible. Since the recognition parameters acquired at the data center are transmitted to the mobile communication terminal, hereafter utterance content recognition can be appropriately performed by the recognition parameters matching the user only by the mobile communication terminal, without the mobile communication terminal transmitting/receiving information with a learning device.

Growing community of inventors

Yokohama, Japan

Akira Hiraiwa