Unsupervised Speech Recognition via Segmental Empirical Output Distribution Matching

12/23/2018
by   Chih-Kuan Yeh, et al.
6

We consider the problem of training speech recognition systems without using any labeled data, under the assumption that the learner can only access to the input utterances and a phoneme language model estimated from a non-overlapping corpus. We propose a fully unsupervised learning algorithm that alternates between solving two sub-problems: (i) learn a phoneme classifier for a given set of phoneme segmentation boundaries, and (ii) refining the phoneme boundaries based on a given classifier. To solve the first sub-problem, we introduce a novel unsupervised cost function named Segmental Empirical Output Distribution Matching, which generalizes the work in (Liu et al., 2017) to segmental structures. For the second sub-problem, we develop an approximate MAP approach to refining the boundaries obtained from Wang et al. (2017). Experimental results on TIMIT dataset demonstrate the success of this fully unsupervised phoneme recognition system, which achieves a phone error rate (PER) of 41.6 supervised systems, we show that with oracle boundaries and matching language model, the PER could be improved to 32.5 supervised system of the same model architecture, demonstrating the great potential of the proposed method.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/24/2021

Unsupervised Speech Recognition

Despite rapid progress in the recent past, current speech recognition sy...
research
04/16/2021

A Masked Segmental Language Model for Unsupervised Natural Language Segmentation

Segmentation remains an important preprocessing step both in languages w...
research
06/06/2019

From Caesar Cipher to Unsupervised Learning: A New Method for Classifier Parameter Estimation

Many important classification problems, such as object classification, s...
research
11/19/2015

Towards Principled Unsupervised Learning

General unsupervised learning is a long-standing conceptual problem in m...
research
01/09/2023

FullStop:Punctuation and Segmentation Prediction for Dutch with Transformers

When applying automated speech recognition (ASR) for Belgian Dutch (Van ...
research
08/01/2016

Blind phoneme segmentation with temporal prediction errors

Phonemic segmentation of speech is a critical step of speech recognition...
research
10/07/2015

Hierarchical Representation of Prosody for Statistical Speech Synthesis

Prominences and boundaries are the essential constituents of prosodic st...

Please sign up or login with your details

Forgot password? Click here to reset