Fine-tuning of Pre-trained End-to-end Speech Recognition with Generative Adversarial Networks

by   Md. Akmal Haidar, et al.

Adversarial training of end-to-end (E2E) ASR systems using generative adversarial networks (GAN) has recently been explored for low-resource ASR corpora. GANs help to learn the true data representation through a two-player min-max game. However, training an E2E ASR model using a large ASR corpus with a GAN framework has never been explored, because it might take excessively long time due to high-variance gradient updates and face convergence issues. In this paper, we introduce a novel framework for fine-tuning a pre-trained ASR model using the GAN objective where the ASR model acts as a generator and a discriminator tries to distinguish the ASR output from the real data. Since the ASR model is pre-trained, we hypothesize that the ASR model output (soft distribution vectors) helps to get higher scores from the discriminator and makes the task of the discriminator harder within our GAN framework, which in turn improves the performance of the ASR model in the fine-tuning stage. Here, the pre-trained ASR model is fine-tuned adversarially against the discriminator using an additional adversarial loss. Experiments on full LibriSpeech dataset show that our proposed approach outperforms baselines and conventional GAN-based adversarial models.


Efficiently Fusing Pretrained Acoustic and Linguistic Encoders for Low-resource Speech Recognition

End-to-end models have achieved impressive results on the task of automa...

Transforming the output of GANs by fine-tuning them with features from different datasets

In this work we present a method for fine-tuning pre-trained GANs with f...

Supervised GAN Watermarking for Intellectual Property Protection

We propose a watermarking method for protecting the Intellectual Propert...

Investigating Generative Adversarial Networks based Speech Dereverberation for Robust Speech Recognition

We investigate the use of generative adversarial networks (GANs) in spee...

Learning not to Discriminate: Task Agnostic Learning for Improving Monolingual and Code-switched Speech Recognition

Recognizing code-switched speech is challenging for Automatic Speech Rec...

Adapting an ASR Foundation Model for Spoken Language Assessment

A crucial part of an accurate and reliable spoken language assessment sy...

Completely Unsupervised Phoneme Recognition By A Generative Adversarial Network Harmonized With Iteratively Refined Hidden Markov Models

Producing a large annotated speech corpus for training ASR systems remai...

Please sign up or login with your details

Forgot password? Click here to reset