NTR Webinar: Learning Efficient Representations for Keyword Spotting with Triplet Loss

NTR organizes and hosts scientific webinars on neural networks and invites speakers from all over the world to present their recent work at the webinars.

On March 9 Roman Vygon, NTR, Tomsk, Russia, led a technical Zoom webinar on Learning Efficient Representations for Keyword Spotting with Triplet Loss. 

About the webinar: 

In the past few years, triplet loss-based metric embeddings have become a de-facto standard for several important computer vision problems, most notably, person re-identification. 

On the other hand, in the area of speech recognition the metric embeddings generated by the triplet loss are rarely used even for classification problems. 

We fill this gap showing that a combination of two representation learning techniques: a triplet loss-based embedding and a variant of kNN for classification instead of cross-entropy loss significantly (by 26% to 38%) improves the classification accuracy for convolutional networks on a LibriSpeech-derived LibriWords datasets.

Materials available:

Webinar presentation.

Moderator and contact:

NTR CEO Nick Mikhailovsky: nickm@ntrlab.com.

Leave a Reply

Your email address will not be published. Required fields are marked *