On-device custom wake word detection

1. A device comprising:

memory including model parameters that define a custom wake word detection model, the wake word detection model including a recurrent neural network transducer (RNNT) and a lookup table (LUT), the LUT indicating a hidden vector to be provided in response to a phoneme of a user-specified wake word;

a microphone to capture audio;

processing circuitry to:

receive the audio from the microphone;

determine, using the wake word detection model, whether the audio includes an utterance of the user-specified wake word;

wake up a personal assistant after determining the audio includes the utterance of the user-specified wake word; and

reset, in response to determining one of the wake word was uttered and a specified period of time has elapsed, the wake word detection model to erase a history of processed audio.

2. The device of claim 1 , wherein the wake word detection model is trained using standard phonemes and whole word phonemes.

3. The device of claim 1 , wherein the wake word detection model is compressed using single value decomposition (SVD).

4. The device of claim 3 , wherein the wake word detection model includes weights quantized to 8-bit or 16-bit values.

5. The device of claim 1 , wherein the processing circuitry is to:

receive the wake word from a user;

provide the wake word to a wake word model engine; and

receive from the wake word model engine, a wake word graph of the wake word indicating a phoneme sequence of the wake word and alternate pronunciations of the wake word;

wherein the wake word graph is part of the wake word detection model.

6. The device of claim 1 , wherein the processing circuitry is to:

receive the wake word from a user;

provide the wake word to a wake word model engine; and

receive from the wake word model engine, a wake word graph of the wake word indicating a phoneme sequence of the wake word and alternate pronunciations of the wake word and a background language model with unigrams and bi-grams of the wake word removed therefrom;

wherein the wake word graph and the background language model are part of the wake word detection model.

7. A method of on-device custom wake word detection comprising:

receiving audio from a microphone of a device;

determining, using a wake word detection model, whether the audio includes an utterance of a user-specified wake word, the wake word detection model including a recurrent neural network transducer (RNNT) and a lookup table (LUT), the LUT indicating a hidden vector to be provided in response to a phoneme of a user-specified wake word;

waking up a personal assistant after determining the audio includes the utterance of the user-specified wake word; and

resetting, in response to determining one of the wake word was uttered and a specified period of time has elapsed, the wake word detection model to erase a history of processed audio.

8. The method of claim 7 , wherein the wake word detection model is trained using standard phonemes and whole word phonemes.

9. The method of claim 7 , wherein the wake word detection model is compressed using single value decomposition (SVD).

10. The method of claim 9 , wherein the wake word detection model includes weights quantized to 8-bit or 16-bit values.

11. The method of claim 7 , further comprising:

receiving the user-specified wake word from a user;

providing the user-specified wake word to a wake word model engine; and

receiving from the wake word model engine, a wake word graph of the user-specified wake word indicating a phoneme sequence of the user-specified wake word and alternate pronunciations of the user-specified wake word;

wherein the wake word graph is part of the wake word detection model.

12. A non-transitory machine-readable medium including instructions that, when executed by a machine, cause the machine to perform operations for on-device custom wake word detection, the operations comprising:

receiving audio from a microphone of a device;

determining, using a wake word detection model, whether the audio includes an utterance of a user-specified wake word, the wake word detection model including a recurrent neural network transducer (RNNT) and a lookup table (LUT), the LUT indicating a hidden vector to be provided in response to a phoneme of a user-specified wake word;

waking up a personal assistant after determining the audio includes the utterance of the user-specified wake word; and

resetting, in response to determining one of the wake word was uttered and a specified period of time has elapsed, the wake word detection model to erase a history of processed audio.

13. The non-transitory machine-readable medium of claim 12 , wherein the wake word detection model is trained using standard phonemes and whole word phonemes.

14. The non-transitory machine-readable medium of claim 12 , wherein the operations further comprise:

receiving the user-specified wake word from a user;

providing the user-specified wake word to a wake word model engine; and

receiving from the wake word model engine, a wake word graph of the user-specified wake word indicating a phoneme sequence of the user-specified wake word and alternate pronunciations of the user-specified wake word;

wherein the wake word graph is part of the wake word detection model.

15. The non-transitory machine-readable medium of claim 12 , wherein the operations further include:

receiving the wake word from a user;

providing the wake word to a wake word model engine; and

receiving from the wake word model engine, a wake word graph of the wake word indicating a phoneme sequence of the wake word and alternate pronunciations of the wake word and a background language model with unigrams and bi-grams of the wake word removed therefrom;

wherein the wake word graph and the background language model are part of the wake word detection model.