# Label-Synchronous Neural Transducer for End-to-End ASR

arXiv: https://arxiv.org/abs/2307.03088 · HTML: https://mlsanity.com/paper/2307.03088/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jul 2023.

## Built on by (most cited first, 3 of 3)

- [Label-Synchronous Neural Transducer for E2E Simultaneous Speech Translation](https://mlsanity.com/paper/2406.04541/) (2024)
- [Lightweight Transducer Based on Frame-Level Criterion](https://mlsanity.com/paper/2409.13698/) (2024)
- [Aligner-Encoders: Self-Attention Transformers Can Be Self-Transducers](https://mlsanity.com/paper/2502.05232/) (2025)

## Abstract (arXiv)

Neural transducers provide a natural way of streaming ASR. However, they augment output sequences with blank tokens which leads to challenges for domain adaptation using text data. This paper proposes a label-synchronous neural transducer (LS-Transducer), which extracts a label-level encoder representation before combining it with the prediction network output. Hence blank tokens are no longer needed and the prediction network can be easily adapted using text data. An Auto-regressive Integrate-and-Fire (AIF) mechanism is proposed to generate the label-level encoder representation while retaining the streaming property. In addition, a streaming joint decoding method is designed to improve ASR accuracy. Experiments show that compared to standard neural transducers, the proposed LS-Transducer gave a 10% relative WER reduction (WERR) for intra-domain Librispeech-100h data, as well as 17% and 19% relative WERRs on cross-domain TED-LIUM2 and AESRC2020 data with an adapted prediction network.