DeepAI AI Chat
Log In Sign Up

Speech Representation Learning Combining Conformer CPC with Deep Cluster for the ZeroSpeech Challenge 2021

by   Takashi Maekaku, et al.
Carnegie Mellon University

We present a system for the Zero Resource Speech Challenge 2021, which combines a Contrastive Predictive Coding (CPC) with deep cluster. In deep cluster, we first prepare pseudo-labels obtained by clustering the outputs of a CPC network with k-means. Then, we train an additional autoregressive model to classify the previously obtained pseudo-labels in a supervised manner. Phoneme discriminative representation is achieved by executing the second-round clustering with the outputs of the final layer of the autoregressive model. We show that replacing a Transformer layer with a Conformer layer leads to a further gain in a lexical metric. Experimental results show that a relative improvement of 35 in a syntactic metric are achieved compared to a baseline method of CPC-small which is trained on LibriSpeech 460h data. We achieve top results in this challenge with the syntactic metric.


page 1

page 2

page 3

page 4


The Interspeech Zero Resource Speech Challenge 2021: Spoken language modelling

We present the Zero Resource Speech Challenge 2021, which asks participa...

DeepCluE: Enhanced Image Clustering via Multi-layer Ensembles in Deep Neural Networks

Deep clustering has recently emerged as a promising technique for comple...

Exploring Non-Contrastive Representation Learning for Deep Clustering

Existing deep clustering methods rely on contrastive learning for repres...

Hybrid Contrastive Learning with Cluster Ensemble for Unsupervised Person Re-identification

Unsupervised person re-identification (ReID) aims to match a query image...

Pseudo-supervised Deep Subspace Clustering

Auto-Encoder (AE)-based deep subspace clustering (DSC) methods have achi...