Abstract
This paper describes a novel approach to improve monoaural
speaker identification where two speakers are present in a
single-microphone recording. The goal is to identify both of
the underlying speakers in the given mixture. The proposed
approach is composed of a double-talk detector (DTD) as a preprocessor
and speaker identification back-end. We demonstrate
that including the double-talk detector improves the speaker
identification accuracy. Experiments on GRID corpus show that
including the DTD improves average recognition accuracy from
96.53% to 97.43%.
speaker identification where two speakers are present in a
single-microphone recording. The goal is to identify both of
the underlying speakers in the given mixture. The proposed
approach is composed of a double-talk detector (DTD) as a preprocessor
and speaker identification back-end. We demonstrate
that including the double-talk detector improves the speaker
identification accuracy. Experiments on GRID corpus show that
including the DTD improves average recognition accuracy from
96.53% to 97.43%.
| Original language | English |
|---|---|
| Journal | Proceedings of the International Conference on Spoken Language Processing |
| Pages (from-to) | 1069-1072 |
| ISSN | 1990-9772 |
| Publication status | Published - 26 Sept 2010 |
| Event | Interspeech 2010 - Makuhari, Japan Duration: 26 Sept 2010 → 30 Sept 2010 |
Conference
| Conference | Interspeech 2010 |
|---|---|
| Country/Territory | Japan |
| City | Makuhari |
| Period | 26/09/2010 → 30/09/2010 |