Techniques for language independent wake-up word detection

1. A method of enabling wake-up word detection in a target language on a user device, the method comprising:

receiving acoustic input of a user speaking a wake-up word in the target language when the user device is in a low-power mode;

providing acoustic features derived from the acoustic input to an acoustic model stored on the user device to obtain a first sequence of speech units corresponding to the wake-up word spoken by the user in the target language, the acoustic model trained on a corpus of training data in a source language different than the target language;

comparing the first sequence of speech units with a reference sequence of speech units to recognize the wake-up word in the target language, wherein the reference sequence of speech units is obtained by applying acoustic features derived from audio comprising the user speaking the wake-up word in the target language to the acoustic model;

responsive to recognizing the wake-up word, transitioning the user device from the low-power mode to an active mode; and

adapting the acoustic model to the user using both the reference sequence of speech units and the first sequence of speech units.

2. The method of claim 1 , further comprising adapting the acoustic model to the user using the acoustic input of the user speaking the wake-up word in the target language and the sequence of speech units obtained therefrom via the acoustic model.

3. The method of claim 1 , wherein the sequence of speech unit comprises a phoneme sequence corresponding to the wake-up word spoken by the user in the target language.

4. The method of claim 1 , further comprising associating at least one task with the wake-up word to be performed when it is determined that the user has spoken the wake-up word.

5. A user device configured to enable wake-up word detection in a target language, the user device comprising:

at least one microphone configured to obtain acoustic information from an environment of the user device;

at least one computer readable medium storing an acoustic model trained on a corpus of training data in a source language different than the target language; and

at least one processor coupled to the at least one computer readable medium and programmed to perform:

receiving, from the at least one microphone, acoustic input from the user speaking a wake-up word in the target language when the user device is in a low-power mode;

providing acoustic features derived from the acoustic input to the acoustic model to obtain a sequence of speech units corresponding to the wake-up word spoken by the user in the target language;

comparing the sequence of speech units to a reference sequence of speech units, wherein the reference sequence of speech units obtained by applying acoustic features derived from audio comprising the user speaking the wake-up word in the target language to the acoustic model; and

adapting the acoustic model to the user using the sequence of speech units and the reference sequence of the speech units.

6. The user device of claim 5 , further comprising adapting the acoustic model to the user using the acoustic input of the user speaking the wake-up word in the target language and the sequence of speech units obtained therefrom via the acoustic model.

7. The user device of claim 5 , wherein the sequence of speech units comprises a phoneme sequence corresponding to the wake-up word spoken by the user in the target language.

8. The user device of claim 5 , further comprising associating at least one task with the wake-up word to be performed when it is determined that the user has spoken the wake-up word in the target language.

9. A method of performing wake-up word detection on a user device, the method comprising:

while the user device is operating in a low-power mode:

receiving acoustic input from a user speaking in a target language;

providing acoustic features derived from the acoustic input to an acoustic model stored on the user device to obtain a first sequence of speech units corresponding to the acoustic input, the acoustic model trained on a corpus of training data in a source language different than the target language;

determining if the user spoke the wake-up word at least in part by comparing the first sequence of speech units to a reference sequence of speech units stored on the user device, wherein the reference sequence of speech units obtained by applying acoustic features derived from audio comprising the user speaking the wake-up word in the target language to the acoustic model;

exiting the low-power mode if it is determined that the user spoke the wake-up word; and

adapting the acoustic model to the user using both the reference sequence of speech units and the first sequence of speech units.

10. The method of claim 9 , wherein the acoustic model was adapted to the user using the audio comprising the user speaking the wake-up word in the target language and the reference sequence of speech units obtained therefrom via the acoustic model.

11. The method of claim 9 , further comprising performing at least one task associated with the wake-up word if it is determined that the user spoke the wake-up word.

12. The method of claim 9 , wherein the first sequence of speech units comprises a phoneme sequence corresponding to the acoustic input, and wherein the reference sequence of speech units comprises a phoneme sequence corresponding to the user speaking the wake-up word in the target language.

13. The method of claim 9 , wherein exiting the low-power mode comprises transitioning the user device from an idle mode to an active mode.