Transfer learning is a vital technique that generalizes models trained for one setting or task
to other settings or tasks. For example in speech recognition, an acoustic model trained for …

We present a structured overview of adaptation algorithms for neural network-based speech
recognition, considering both hybrid hidden Markov model/neural network systems and end …

The external language models (LM) integration remains a challenging task for end-to-end
(E2E) automatic speech recognition (ASR) which has no clear division between acoustic …

We propose a novel regularized adaptation technique for context dependent deep neural
network hidden Markov models (CD-DNN-HMMs). The CD-DNN-HMM has a large output …

This paper proposes a simple yet effective model-based neural network speaker adaptation
technique that learns speaker-specific hidden unit contributions given adaptation data …

In this paper, we propose a new fast speaker adaptation method for the hybrid NN-HMM
speech recognition model. The adaptation method depends on a joint learning of a large …

Fast adaptation of deep neural networks (DNN) is an important research topic in deep
learning. In this paper, we have proposed a general adaptation scheme for DNN based on …

The efficacy of external language model (LM) integration with existing end-to-end (E2E)
automatic speech recognition (ASR) systems can be improved significantly using the …

This paper presents an improved transfer learning framework applied to robust personalised
speech recognition models for speakers with dysarthria. As the baseline of transfer learning …

Speaker variability is one of the major error sources for ASR systems. Speaker adaptation
estimates speaker specific models from the speaker independent ones to minimize the …