# Maximum a Posteriori Adaptation of Network Parameters in Deep Models

arXiv: https://arxiv.org/abs/1503.02108 · HTML: https://mlsanity.com/paper/1503.02108/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Mar 2015.

## Built on by (most cited first, 5 of 5)

- [Recent Advances in End-to-End Automatic Speech Recognition](https://mlsanity.com/paper/2111.01690/) (2021)
- [Deep Transfer Learning for Automatic Speech Recognition: Towards Better Generalization](https://mlsanity.com/paper/2304.14535/) (2023)
- [A Variational Bayesian Approach to Learning Latent Variables for Acoustic Knowledge Transfer](https://mlsanity.com/paper/2110.08598/) (2021)
- [Homogeneous Speaker Features for On-the-Fly Dysarthric and Elderly Speaker Adaptation](https://mlsanity.com/paper/2407.06310/) (2024)
- [Optimal Transport-based Adaptation in Dysarthric Speech Tasks](https://mlsanity.com/paper/2104.02535/) (2021)

## Abstract (arXiv)

We present a Bayesian approach to adapting parameters of a well-trained context-dependent, deep-neural-network, hidden Markov model (CD-DNN-HMM) to improve automatic speech recognition performance. Given an abundance of DNN parameters but with only a limited amount of data, the effectiveness of the adapted DNN model can often be compromised. We formulate maximum a posteriori (MAP) adaptation of parameters of a specially designed CD-DNN-HMM with an augmented linear hidden networks connected to the output tied states, or senones, and compare it to feature space MAP linear regression previously proposed. Experimental evidences on the 20,000-word open vocabulary Wall Street Journal task demonstrate the feasibility of the proposed framework. In supervised adaptation, the proposed MAP adaptation approach provides more than 10% relative error reduction and consistently outperforms the conventional transformation based methods. Furthermore, we present an initial attempt to generate hierarchical priors to improve adaptation efficiency and effectiveness with limited adaptation data by exploiting similarities among senones.