Method for increasing the voice recognition rate of a voice recognition calling device

• US 6,131,044 A
• Filed: 04/22/1998
• Issued: 10/10/2000
• Est. Priority Date: 06/09/1997
• Status: Expired due to Term

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Ryu, Yeoung-Moo
• Primary Examiner(s): Maung, Nay
• Assistant Examiner(s): Vuong, Quochien B.
• Application Number:
  US09/064,282
• Time in Patent Office: 902 Days
• Field of Search: 455/79, 455/563, 704/226, 704/228, 704/233, 704/270, 704/275, 379/420, 379/67.1, 379/69, 379/70, 379/82, 379/88.01, 379/88.03, 379/106.09, 379/386
• US Class Current: 455/563
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 21/0364 for improving intelligibility
• 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
• CPC Class Codes: H04M 1/271 controlled by voice recognition

Abstract

A method for increasing the voice recognition rate in a voice recognition calling device wherein the frequencies of a ring sound are separated from those of a voice bandwidth to enable the application of input voice from a combined voice and ring input to a voice recognition processor. In an alternative embodiment, the duration of the ring sound is shortened to increase the voice recognition rate of a voice recognition calling device.

Claims

1. A method for processing voice commands to receive a call over a voice recognition calling device having a speakerphone, comprising the steps of:

a) differentiating a frequency bandwidth of a ring sound generated by the calling device from a frequency bandwidth of the voice commands using a bandpass filter, wherein said frequency bandwidth of the ring sound is higher than the frequency bandwidth of the voice command; and

b) receiving the ring through the speakerphone upon input of voice commands for receiving the call over the speakerphone.

2. The method according to claim 1, wherein the frequency bandwidth of the ring, sound is 1.8-2.2 kHz.

3. The method according to claim 1, wherein frequency bandwidth of the voice input in 300 Hz-1.5 kHz.

4. The method according to claim 1, further comprising the step of generating a ring having a 0.5 second ring-on and a 5.5 second ring-off cycle, said step of generating being performed prior to said step of receiving.

5. A method for processing voice commands in a voice recognition calling device comprising the steps of:

a) setting an input voice command frequency bandwidth of 300 Hz-1.5 kHz;

b) setting a ring frequency bandwidth different than said voice command bandwidth, said ring frequency bandwidth having a lower frequency limit greater than 1.5 kHz; and

c) receiving a ring sound through a speaker of the voice recognition calling device upon input of a voice command initiating an incoming telephone call.

6. The method according to claim 5, further comprising the step of generating a ring having a 0.5 second ring-on and a 5.5 second ring-off cycle when a ring signal is received by the voice recognition device.