# Data-selective Transfer Learning for Multi-Domain Speech Recognition

arXiv: https://arxiv.org/abs/1509.02409 · HTML: https://mlsanity.com/paper/1509.02409/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Sep 2015.

## Built on by (most cited first, 3 of 3)

- [Deep Transfer Learning for Automatic Speech Recognition: Towards Better Generalization](https://mlsanity.com/paper/2304.14535/) (2023)
- [Summaries as Captions: Generating Figure Captions for Scientific Documents with Automated Text Summarization](https://mlsanity.com/paper/2302.12324/) (2023)
- [Pretext Tasks selection for multitask self-supervised speech representation learning](https://mlsanity.com/paper/2107.00594/) (2021)

## Abstract (arXiv)

Negative transfer in training of acoustic models for automatic speech recognition has been reported in several contexts such as domain change or speaker characteristics. This paper proposes a novel technique to overcome negative transfer by efficient selection of speech data for acoustic model training. Here data is chosen on relevance for a specific target. A submodular function based on likelihood ratios is used to determine how acoustically similar each training utterance is to a target test set. The approach is evaluated on a wide-domain data set, covering speech from radio and TV broadcasts, telephone conversations, meetings, lectures and read speech. Experiments demonstrate that the proposed technique both finds relevant data and limits negative transfer. Results on a 6--hour test set show a relative improvement of 4% with data selection over using all data in PLP based models, and 2% with DNN features.