# L-Vector: Neural Label Embedding for Domain Adaptation

arXiv: https://arxiv.org/abs/2004.13480 · HTML: https://mlsanity.com/paper/2004.13480/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Apr 2020.

## Built on by (most cited first, 9 of 9)

- [Internal Language Model Training for Domain-Adaptive End-to-End Speech Recognition](https://mlsanity.com/paper/2102.01380/) (2021)
- [Minimum Word Error Rate Training with Language Model Fusion for End-to-End Speech Recognition](https://mlsanity.com/paper/2106.02302/) (2021)
- [Internal Language Model Adaptation with Text-Only Data for End-to-End Speech Recognition](https://mlsanity.com/paper/2110.05354/) (2021)
- [Modular Hybrid Autoregressive Transducer](https://mlsanity.com/paper/2210.17049/) (2022)
- [Boosting Cross-Domain Speech Recognition with Self-Supervision](https://mlsanity.com/paper/2206.09783/) (2022)
- [Wav2vec-S: Semi-Supervised Pre-Training for Low-Resource ASR](https://mlsanity.com/paper/2110.04484/) (2021)
- [Explicit Intensity Control for Accented Text-to-speech](https://mlsanity.com/paper/2210.15364/) (2022)
- [A Variational Bayesian Approach to Learning Latent Variables for Acoustic Knowledge Transfer](https://mlsanity.com/paper/2110.08598/) (2021)
- [Learning Separable Hidden Unit Contributions for Speaker-Adaptive Lip-Reading](https://mlsanity.com/paper/2310.05058/) (2023)

## Abstract (arXiv)

We propose a novel neural label embedding (NLE) scheme for the domain adaptation of a deep neural network (DNN) acoustic model with unpaired data samples from source and target domains. With NLE method, we distill the knowledge from a powerful source-domain DNN into a dictionary of label embeddings, or l-vectors, one for each senone class. Each l-vector is a representation of the senone-specific output distributions of the source-domain DNN and is learned to minimize the average L2, Kullback-Leibler (KL) or symmetric KL distance to the output vectors with the same label through simple averaging or standard back-propagation. During adaptation, the l-vectors serve as the soft targets to train the target-domain model with cross-entropy loss. Without parallel data constraint as in the teacher-student learning, NLE is specially suited for the situation where the paired target-domain data cannot be simulated from the source-domain data. We adapt a 6400 hours multi-conditional US English acoustic model to each of the 9 accented English (80 to 830 hours) and kids' speech (80 hours). NLE achieves up to 14.1% relative word error rate reduction over direct re-training with one-hot labels.