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

• US 20050102134A1
• Filed: 09/14/2004
• Published: 05/12/2005
• Est. Priority Date: 09/19/2003
• Status: Active Grant

• Current Assignee: NTT Docomo Incorporated (Nippon Telegraph and Telephone Corporation)
• Original Assignee: NTT Docomo Incorporated (Nippon Telegraph and Telephone Corporation)
• Inventors: Sugimura, Toshiaki, Miki, Toshio, Hayashi, Kouki, Hiraiwa, Akira, Manabe, Hiroyuki, Hiraiwa, Yumiko
• Granted Patent: US 7,627,470 B2
• Time in Patent Office: Days
• US Class Current: 704/207
• CPC Class Codes: G06F 3/015 Input arrangements based on nervous system activity detection, e.g. brain waves [EEG] detection, electromyograms [EMG] detection, electrodermal response detection
• CPC Class Codes: G10L 15/25 using position of the lips, movement of the lips or face analysis
• CPC Class Codes: G10L 25/78 Detection of presence or absence of voice signals switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M9/10

Abstract

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.

Claims

1. A speaking period detection device comprising:

EMG detection means for detecting an EMG generated while a speaker is speaking; and

speaking period detection means for detecting a speaking period based on the EMG detected by the EMG detection means;

wherein the device derives information relating to the speaking period detected by the speaking period detection means.

2. The speaking period detection device according to claim 1, wherein the EMG detection means detects the EMG from electrodes provided on a portion of the case of a terminal used by the speaker for speaking, the portion being in contact with the speaker'"'"'s skin while the speaker is speaking.

3. The speaking period detection device according to claim 1, wherein the speaking period detection means compares an amplitude value of the EMG with a predetermined threshold to detect speech start timing and speech end timing of the speaking period.

4. The speaking period detection device according to claim 2, wherein the speaking period detection means compares an amplitude value of the EMG with a predetermined threshold to detect speech start timing and speech end timing of the speaking period.

5. The speaking period detection device according to claim 1, further comprising a counter for counting the result of the comparison of the amplitude value of the EMG and the predetermined threshold, wherein the speaking period detection means determines a speaking period only when the count value of the counter exceeds a predetermined value.

6. The speaking period detection device according to claim 2, further comprising a counter for counting the result of the comparison of the amplitude value of the EMG and the predetermined threshold, wherein the speaking period detection means determines a speaking period only when the count value of the counter exceeds a predetermined value.

7. The speaking period detection device according to claim 3, further comprising a counter for counting the result of the comparison of the amplitude value of the EMG and the predetermined threshold, wherein the speaking period detection means determines a speaking period only when the count value of the counter exceeds a predetermined value.

8. The speaking period detection device according to claim 4, further comprising a counter for counting the result of the comparison of the amplitude value of the EMG and the predetermined threshold, wherein the speaking period detection means determines a speaking period only when the count value of the counter exceeds a predetermined value.

9. The speaking period detection device according to claim 1, further comprising storage means for saving a speaking voice signal of the speaker;

wherein saving of the speaking voice signal is started at the speech start timing and ended at the speech end timing.

10. The speaking period detection device according to claim 2, further comprising storage means for saving a speaking voice signal of the speaker;

wherein saving of the speaking voice signal is started at the speech start timing and ended at the speech end timing.

11. The speaking period detection device according to claim 3, further comprising storage means for saving a speaking voice signal of the speaker;

wherein saving of the speaking voice signal is started at the speech start timing and ended at the speech end timing.

12. The speaking period detection device according to claim 4, further comprising storage means for saving a speaking voice signal of the speaker;

wherein saving of the speaking voice signal is started at the speech start timing and ended at the speech end timing.

13. The speaking period detection device according to claim 5, further comprising storage means for saving a speaking voice signal of the speaker;

wherein saving of the speaking voice signal is started at the speech start timing and ended at the speech end timing.

14. The speaking period detection device according to claim 6, further comprising storage means for saving a speaking voice signal of the speaker;

wherein saving of the speaking voice signal is started at the speech start timing and ended at the speech end timing.

15. The speaking period detection device according to claim 7, further comprising storage means for saving a speaking voice signal of the speaker;

wherein saving of the speaking voice signal is started at the speech start timing and ended at the speech end timing.

16. The speaking period detection device according to claim 8, further comprising storage means for saving a speaking voice signal of the speaker;

wherein saving of the speaking voice signal is started at the speech start timing and ended at the speech end timing.

17. A voice recognition processing device for performing a voice recognition processing for a speaking voice signal, the voice recognition processing device comprising voice recognition processing means for performing a voice recognition processing for a speaking voice signal corresponding to a speaking period detected by the speaking period detection device according to any one of claims 1 to 8.

18. A voice recognition processing device for performing a voice recognition processing for a speaking voice signal, the voice recognition processing device comprising voice recognition processing means for performing a voice recognition processing for a speaking voice signal stored in the storage means by the speaking period detection device according to any of claims 9 to 16.

19. A transmission system for performing a coding processing for a speaking voice signal corresponding to a speaking period and transmitting the coded voice signal, the transmission system comprising coding processing timing determination means for determining timing of the coding processing based on a speaking period detected by the speaking period detection device according to any one of claims 1 to 16.

20. A signal level control device for controlling a level of an output signal derived from a microphone, the signal level control device comprising control means for controlling the level of an output signal based on a speaking period detected by the speaking period detection device according to any one of claims 1 to 16, and controlling a voice corresponding to a non-speaking period not to be outputted.

21. A speaking period detection method comprising:

an EMG detection step of detecting an EMG generated while a speaker is speaking; and

a speaking period detection step of detecting a speaking period based on the EMG detected at the EMG detection step;

wherein information relating to the speaking period detected at the speaking period detection step is notified.