# Listen, Attend, Spell and Adapt: Speaker Adapted Sequence-to-Sequence ASR

arXiv: https://arxiv.org/abs/1907.04916 · HTML: https://mlsanity.com/paper/1907.04916/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jul 2019.

## Built on by (most cited first, 8 of 8)

- [Recent Advances in End-to-End Automatic Speech Recognition](https://mlsanity.com/paper/2111.01690/) (2021)
- [End-to-End Speech Recognition: A Survey](https://mlsanity.com/paper/2303.03329/) (2023)
- [Automatic Speech Recognition using Advanced Deep Learning Approaches: A survey](https://mlsanity.com/paper/2403.01255/) (2024)
- [Deep Transfer Learning for Automatic Speech Recognition: Towards Better Generalization](https://mlsanity.com/paper/2304.14535/) (2023)
- [Conformer with dual-mode chunked attention for joint online and offline ASR](https://mlsanity.com/paper/2206.11157/) (2022)
- [Dual-Encoder Architecture with Encoder Selection for Joint Close-Talk and Far-Talk Speech Recognition](https://mlsanity.com/paper/2109.08744/) (2021)
- [ChannelAugment: Improving generalization of multi-channel ASR by training with input channel randomization](https://mlsanity.com/paper/2109.11225/) (2021)
- [Speaker-Adapted End-to-End Visual Speech Recognition for Continuous Spanish](https://mlsanity.com/paper/2311.12480/) (2023)

## Abstract (arXiv)

Sequence-to-sequence (seq2seq) based ASR systems have shown state-of-the-art performances while having clear advantages in terms of simplicity. However, comparisons are mostly done on speaker independent (SI) ASR systems, though speaker adapted conventional systems are commonly used in practice for improving robustness to speaker and environment variations. In this paper, we apply speaker adaptation to seq2seq models with the goal of matching the performance of conventional ASR adaptation. Specifically, we investigate Kullback-Leibler divergence (KLD) as well as Linear Hidden Network (LHN) based adaptation for seq2seq ASR, using different amounts (up to 20 hours) of adaptation data per speaker. Our SI models are trained on large amounts of dictation data and achieve state-of-the-art results. We obtained 25% relative word error rate (WER) improvement with KLD adaptation of the seq2seq model vs. 18.7% gain from acoustic model adaptation in the conventional system. We also show that the WER of the seq2seq model decreases log-linearly with the amount of adaptation data. Finally, we analyze adaptation based on the minimum WER criterion and adapting the language model (LM) for score fusion with the speaker adapted seq2seq model, which result in further improvements of the seq2seq system performance.