# Embedding-Based Speaker Adaptive Training of Deep Neural Networks

arXiv: https://arxiv.org/abs/1710.06937 · HTML: https://mlsanity.com/paper/1710.06937/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Oct 2017.

## Built on by (most cited first, 7 of 7)

- [Hardware-aware training for large-scale and diverse deep learning inference workloads using in-memory computing-based accelerators](https://mlsanity.com/paper/2302.08469/) (2023)
- [ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training](https://mlsanity.com/paper/2104.11125/) (2021)
- [4-bit Quantization of LSTM-based Speech Recognition Models](https://mlsanity.com/paper/2108.12074/) (2021)
- [TS-Net: OCR Trained to Switch Between Text Transcription Styles](https://mlsanity.com/paper/2103.05489/) (2021)
- [Towards Writing Style Adaptation in Handwriting Recognition](https://mlsanity.com/paper/2302.06318/) (2023)
- [FedEmbed: Personalized Private Federated Learning](https://mlsanity.com/paper/2202.09472/) (2022)
- [Unbiased Single-scale and Multi-scale Quantizers for Distributed Optimization](https://mlsanity.com/paper/2109.12497/) (2021)

## Abstract (arXiv)

An embedding-based speaker adaptive training (SAT) approach is proposed and investigated in this paper for deep neural network acoustic modeling. In this approach, speaker embedding vectors, which are a constant given a particular speaker, are mapped through a control network to layer-dependent element-wise affine transformations to canonicalize the internal feature representations at the output of hidden layers of a main network. The control network for generating the speaker-dependent mappings is jointly estimated with the main network for the overall speaker adaptive acoustic modeling. Experiments on large vocabulary continuous speech recognition (LVCSR) tasks show that the proposed SAT scheme can yield superior performance over the widely-used speaker-aware training using i-vectors with speaker-adapted input features.