L-Vector: Neural Label Embedding for Domain Adaptation

by   Zhong Meng, et al.

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.


page 1

page 2

page 3

page 4


Domain Adaptation Using Class Similarity for Robust Speech Recognition

When only limited target domain data is available, domain adaptation cou...

Large-Scale Domain Adaptation via Teacher-Student Learning

High accuracy speech recognition requires a large amount of transcribed ...

Teacher-Student Consistency For Multi-Source Domain Adaptation

In Multi-Source Domain Adaptation (MSDA), models are trained on samples ...

Relational Teacher Student Learning with Neural Label Embedding for Device Adaptation in Acoustic Scene Classification

In this paper, we propose a domain adaptation framework to address the d...

Domain Expansion in DNN-based Acoustic Models for Robust Speech Recognition

Training acoustic models with sequentially incoming data – while both le...

Appearance Based Deep Domain Adaptation for the Classification of Aerial Images

This paper addresses domain adaptation for the pixel-wise classification...

Teacher-Student Domain Adaptation for Biosensor Models

We present an approach to domain adaptation, addressing the case where d...

Please sign up or login with your details

Forgot password? Click here to reset