Mobile electronic device and real-time call translation method thereof

Abstract

This case discloses a mobile electronic device and its real-time call translation method. The real-time call translation method is applicable to mobile electronic devices including a microphone, and the method includes the following steps: When a voice call is initiated, ambient volume is detected. A speech recognition parameter is determined based on the ambient volume. Based on the speech recognition parameter, speech recognition processing is performed on a call voice signal received by the microphone to obtain a dialogue text. The dialogue text corresponding to a first language is translated to generate a translated dialogue text corresponding to a second language. During the voice call, a function is performed based on the translated dialogue text.

Claims

1. A method for real-time translation during a call, applicable to a mobile electronic device including a microphone, the method comprising: When a voice call is initiated, the ambient volume is detected. A speech recognition parameter is determined based on the ambient volume. Based on the speech recognition parameters, speech recognition processing is performed on a call voice signal received by the microphone to obtain a dialogue text; the dialogue text corresponding to the first language is translated to generate a translated dialogue text corresponding to the second language; and during the voice call, a function is performed based on the translated dialogue text; wherein the speech recognition parameters include an end-of-speech timeout (EOS timeout) of the speech recognition processing, and the step of determining the speech recognition parameters based on the ambient volume includes: determining the end-of-speech timeout based on the call mode of the voice call and the ambient volume; When the ambient volume is greater than a volume threshold and the call mode is amplified mode, the voice call timeout is determined to be a first value; and when the ambient volume is greater than the volume threshold and the call mode is earpiece mode, the voice call timeout is determined to be a second value, wherein the second value is greater than the first value.

2. The instant call translation method as described in claim 1, wherein the step of determining the speech recognition parameters based on the ambient volume includes: When the ambient volume is greater than a volume threshold, the voice end timeout is determined to be a first value; and when the ambient volume is not greater than the volume threshold, the voice end timeout is determined to be a second value, wherein the second value is greater than the first value.

3. The instant call translation method as described in claim 1, wherein the step of determining the voice end timeout based on the call mode and the ambient volume includes: When the ambient volume is not greater than the volume threshold and the call mode is amplification mode, the voice end timeout is determined to be the third value. And when the ambient volume is not greater than the volume threshold and the call mode is earpiece mode, the voice end timeout is determined to be a fourth value, wherein the fourth value is greater than the third value, and the third value is greater than the second value.

4. The instant call translation method as described in claim 1, wherein prior to the step of performing speech recognition processing based on the call voice signal received by the microphone according to the speech recognition parameters to obtain the dialogue text, the method further includes: Based on the call mode of the voice call, determine an audio processing parameter; And, based on the audio processing parameters, perform an audio adjustment on the call voice signal received by the microphone.

5. The instant call translation method as described in claim 4, wherein the audio processing parameters include microphone sensitivity, the call mode includes a speaker mode or a handset mode, and the microphone sensitivity in the speaker mode is higher than the microphone sensitivity in the handset mode.

6. The instant translation method for a call as described in claim 4, wherein the step of determining the audio processing parameters based on the call mode of the voice call includes: When the call mode is amplification mode, adjust the equalizer gain corresponding to the first frequency range; And when the call mode is earpiece mode, adjust the equalizer gain corresponding to the second frequency range, wherein the first frequency range is different from the second frequency range.

7. The instant translation method for a call as described in claim 1, wherein the step of performing the function based on the translated dialogue text during the voice call includes: Perform text-to-speech processing on the translated dialogue text to generate translated speech; And transmit the translated voice to the receiving end of the voice call.

8. A mobile electronic device, comprising: One microphone; A processor, coupled to the microphone, and configured to: detect ambient volume when a voice call is initiated; A speech recognition parameter is determined based on the ambient volume; based on the speech recognition parameter, speech recognition processing is performed on a call voice signal received by the microphone to obtain a dialogue text; the dialogue text corresponding to a first language is translated to generate a translated dialogue text corresponding to a second language; and during the voice call, a function is performed based on the translated dialogue text; wherein the speech recognition parameter includes an end-of-speech timeout (EOS timeout) of the speech recognition processing, and the step of determining the speech recognition parameter based on the ambient volume includes: determining the end-of-speech timeout based on the call mode of the voice call and the ambient volume; When the ambient volume is greater than a volume threshold and the call mode is amplified mode, the voice call timeout is determined to be a first value; and when the ambient volume is greater than the volume threshold and the call mode is earpiece mode, the voice call timeout is determined to be a second value, wherein the second value is greater than the first value.

Images