Voice communication method, voice communication apparatus, and voice communication system

A method for improving security of voice communication at a voice communication apparatus on a receiving side, the method comprising:

• receiving voice information transmitted from a peer device;
• collecting first environmental information of the voice communication apparatus on the receiving side;
• determining whether the first environmental information meets a voice output condition;
• in response to determining that the first environmental information meets the voice output condition, outputting the voice information;
• and
• in response to determining that the first environmental information does not meet the voice output condition, prohibiting the output of the voice information,
• wherein the step of determining whether the first environmental information meets the voice output condition comprises one or more of the steps of:
• determining whether there is only one voice recipient;
• determining whether facial features of the voice recipient are consistent with facial features of a preset receiving user;
• or
• determining whether distances from other users than the voice recipient to the voice recipient exceed a preset threshold.

A voice communication apparatus on a transmitting side for improving security of voice communication, the apparatus comprising:

• a processor;
• and
• a memory storing instructions which, when executed by the processor, cause the processor to:
• obtain voice information from a sound sensor;
• determine whether the voice information is uttered by a preset user;
• in response to determining that the voice information is uttered by the preset user;
• determine a voice environment in which the voice communication apparatus on the transmitting side is located;
• perform optimization processing on the voice information according to the voice environment;
• and
• transmit, via a communicator, the optimized voice information to a peer device;
• and
• in response to determining that the voice information is not uttered by the preset user, prohibit the transmission of the voice information,
• wherein the instructions which, when executed by the processor, further cause the processor to:
• determine whether there is noise in the vicinity of the voice communication apparatus on the transmitting side according to the obtained voice environment;
• determine the volume of the noise when there is noise;
• and
• perform a noise reduction processing on the voice information and increase the volume of the voice information when the volume of the noise is greater than a threshold, and
• wherein the instructions which, when executed by the processor, further cause the processor to:
• obtain facial features of a person who utters the voice information, and determine whether the facial features are consistent with facial features of the preset user;
• or
• obtain action features of the person who utters the voice information, and determining whether the action features are consistent with action features of the preset user.