# Improving Generalization of Deep Neural Network Acoustic Models with Length Perturbation and N-best Based Label Smoothing

arXiv: https://arxiv.org/abs/2203.15176 · HTML: https://mlsanity.com/paper/2203.15176/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 35 references that are in the map.
- First posted on arXiv 29 Mar 2022.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Speech Recognition with Deep Recurrent Neural Networks](https://mlsanity.com/paper/1303.5778/) (2013)
- [Streaming End-to-end Speech Recognition For Mobile Devices](https://mlsanity.com/paper/1811.06621/) (2018)
- [Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates](https://mlsanity.com/paper/1708.07120/) (2017)
- [Towards better decoding and language model integration in sequence to sequence models](https://mlsanity.com/paper/1612.02695/) (2016)
- [A Density Ratio Approach to Language Model Fusion in End-To-End Automatic Speech Recognition](https://mlsanity.com/paper/2002.11268/) (2020)
- [Improving RNN Transducer Modeling for End-to-End Speech Recognition](https://mlsanity.com/paper/1909.12415/) (2019)
- [Advancing RNN Transducer Technology for Speech Recognition](https://mlsanity.com/paper/2103.09935/) (2021)
- [Improved training of end-to-end attention models for speech recognition](https://mlsanity.com/paper/1805.03294/) (2018)
- [Improving sequence-to-sequence speech recognition training with on-the-fly data augmentation](https://mlsanity.com/paper/1910.13296/) (2019)
- [MaskCycleGAN-VC: Learning Non-parallel Voice Conversion with Filling in Frames](https://mlsanity.com/paper/2102.12841/) (2021)
- [Towards Understanding Label Smoothing](https://mlsanity.com/paper/2006.11653/) (2020)
- [The Effectiveness of Time Stretching for Enhancing Dysarthric Speech for Improved Dysarthric Speech Recognition](https://mlsanity.com/paper/2201.04908/) (2022)
- [SpliceOut: A Simple and Efficient Audio Augmentation Method](https://mlsanity.com/paper/2110.00046/) (2021)

## Built on by (most cited first, 2 of 2)

- [Regroup Median Loss for Combating Label Noise](https://mlsanity.com/paper/2312.06273/) (2023)
- [Revisiting the Role of Label Smoothing in Enhanced Text Sentiment Classification](https://mlsanity.com/paper/2312.06522/) (2023)

## Abstract (arXiv)

We introduce two techniques, length perturbation and n-best based label smoothing, to improve generalization of deep neural network (DNN) acoustic models for automatic speech recognition (ASR). Length perturbation is a data augmentation algorithm that randomly drops and inserts frames of an utterance to alter the length of the speech feature sequence. N-best based label smoothing randomly injects noise to ground truth labels during training in order to avoid overfitting, where the noisy labels are generated from n-best hypotheses. We evaluate these two techniques extensively on the 300-hour Switchboard (SWB300) dataset and an in-house 500-hour Japanese (JPN500) dataset using recurrent neural network transducer (RNNT) acoustic models for ASR. We show that both techniques improve the generalization of RNNT models individually and they can also be complementary. In particular, they yield good improvements over a strong SWB300 baseline and give state-of-art performance on SWB300 using RNNT models.