Transfer learning for speech and language processing
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 …
to other settings or tasks. For example in speech recognition, an acoustic model trained for …
Adaptation algorithms for neural network-based speech recognition: An overview
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 …
recognition, considering both hybrid hidden Markov model/neural network systems and end …
Internal language model estimation for domain-adaptive end-to-end speech recognition
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 …
(E2E) automatic speech recognition (ASR) which has no clear division between acoustic …
KL-divergence regularized deep neural network adaptation for improved large vocabulary speech recognition
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 …
network hidden Markov models (CD-DNN-HMMs). The CD-DNN-HMM has a large output …
Learning hidden unit contributions for unsupervised speaker adaptation of neural network acoustic models
P Swietojanski, S Renals - 2014 IEEE Spoken Language …, 2014 - ieeexplore.ieee.org
This paper proposes a simple yet effective model-based neural network speaker adaptation
technique that learns speaker-specific hidden unit contributions given adaptation data …
technique that learns speaker-specific hidden unit contributions given adaptation data …
Fast speaker adaptation of hybrid NN/HMM model for speech recognition based on discriminative learning of speaker code
O Abdel-Hamid, H Jiang - 2013 IEEE International Conference …, 2013 - ieeexplore.ieee.org
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 …
speech recognition model. The adaptation method depends on a joint learning of a large …
Fast adaptation of deep neural network based on discriminant codes for speech recognition
S Xue, O Abdel-Hamid, H Jiang… - IEEE/ACM Transactions …, 2014 - ieeexplore.ieee.org
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 …
learning. In this paper, we have proposed a general adaptation scheme for DNN based on …
Internal language model training for domain-adaptive end-to-end speech recognition
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 …
automatic speech recognition (ASR) systems can be improved significantly using the …
Source domain data selection for improved transfer learning targeting dysarthric speech recognition
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 …
speech recognition models for speakers with dysarthria. As the baseline of transfer learning …
[PDF][PDF] Comparison of discriminative input and output transformations for speaker adaptation in the hybrid NN/HMM systems.
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 …
estimates speaker specific models from the speaker independent ones to minimize the …