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 Labs, 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.