| 摘要 |
Method for speaker identification includes detecting a target speaker's utterance locally; extracting features from the detected utterance locally, analyzing the extracted features in the local device to obtain information on the speaker identification and/or encoding the extracted features locally, transmitting the encoded extracted features to a remote server, decoding and analyzing the received extracted features by the server to obtain information on the speaker identification, and transmitting the information on the speaker identification from the server to the location where the speaker's utterance was detected. The method further includes detecting speech activity locally. Extracting features, encoding the extracted features, and/or transmitting the encoded extracted features to the server, are only performed if speech activity above some predetermined threshold is detected. |
