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

NTR organizes and hosts technical webinars about neural networks and invites speakers from all over the world to lead them. Webinars are held on Tuesdays and most are in Russian. 

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 (in English)

Webinar recording on YouTube (in Russian)

Moderator and contact:

NTR CEO Nick Mikhailovsky: nickm@ntrlab.com.

Leave a Reply

Your email address will not be published.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