Weakly Supervised Multi-Embeddings Learning of Acoustic Models

2014/12/20 by Synnaeve, Gabriel, Dupoux, Emmanuel
#Computation and Language (cs.CL) #FOS: Computer and information sciences #I.2.6 #I.2.7 #I.5.1 #Machine Learning (cs.LG) #Sound (cs.SD)

paper · doi:10.48550/arxiv.1412.6645

Abstract

We trained a Siamese network with multi-task same/different information on a speech dataset, and found that it was possible to share a network for both tasks without a loss in performance. The first task was to discriminate between two same or different words, and the second was to discriminate between two same or different talkers.

Related

• Sampling strategies in Siamese Networks for unsupervised speech representation learning
• Learning weakly supervised multimodal phoneme embeddings
• Additional Shared Decoder on Siamese Multi-view Encoders for Learning Acoustic Word Embeddings
• Deep convolutional acoustic word embeddings using word-pair side\n information
• Learning Joint Acoustic-Phonetic Word Embeddings