# Aligner-Encoders: Self-Attention Transformers Can Be Self-Transducers

arXiv: https://arxiv.org/abs/2502.05232 · HTML: https://mlsanity.com/paper/2502.05232/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 54 references that are in the map.
- First posted on arXiv 6 Feb 2025.

## Builds on (most cited first, 30 of 39)

- [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)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [Attention-Based Models for Speech Recognition](https://mlsanity.com/paper/1506.07503/) (2015)
- [Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss](https://mlsanity.com/paper/2002.02562/) (2020)
- [A Comparative Study on Transformer vs RNN in Speech Applications](https://mlsanity.com/paper/1909.06317/) (2019)
- [State-of-the-art Speech Recognition With Sequence-to-Sequence Models](https://mlsanity.com/paper/1712.01769/) (2017)
- [End-to-End Attention-based Large Vocabulary Speech Recognition](https://mlsanity.com/paper/1508.04395/) (2015)
- [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)
- [Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation](https://mlsanity.com/paper/1612.01744/) (2016)
- [Hybrid Autoregressive Transducer (hat)](https://mlsanity.com/paper/2003.07705/) (2020)
- [Towards better decoding and language model integration in sequence to sequence models](https://mlsanity.com/paper/1612.02695/) (2016)
- [Exploring Architectures, Data and Units For Streaming End-to-End Speech Recognition with RNN-Transducer](https://mlsanity.com/paper/1801.00841/) (2018)
- [E-Branchformer: Branchformer with Enhanced merging for speech recognition](https://mlsanity.com/paper/2210.00077/) (2022)
- [Transformer-based Acoustic Modeling for Hybrid Speech Recognition](https://mlsanity.com/paper/1910.09799/) (2019)
- [Online and Linear-Time Attention by Enforcing Monotonic Alignments](https://mlsanity.com/paper/1704.00784/) (2017)
- [CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition](https://mlsanity.com/paper/1905.11235/) (2019)
- [Transformer-Transducer: End-to-End Speech Recognition with Self-Attention](https://mlsanity.com/paper/1910.12977/) (2019)
- [End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Results](https://mlsanity.com/paper/1412.1602/) (2014)
- [Alignment Restricted Streaming Recurrent Neural Network Transducer](https://mlsanity.com/paper/2011.03072/) (2020)
- [Factorized Neural Transducer for Efficient Language Model Adaptation](https://mlsanity.com/paper/2110.01500/) (2021)
- [Large-Scale Streaming End-to-End Speech Translation with Neural Transducers](https://mlsanity.com/paper/2204.05352/) (2022)
- [RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutions](https://mlsanity.com/paper/2005.03271/) (2020)
- [Pseudo Label Is Better Than Human Label](https://mlsanity.com/paper/2203.12668/) (2022)
- [Self-Attention Transducers for End-to-End Speech Recognition](https://mlsanity.com/paper/1909.13037/) (2019)

## Built on by (most cited first, 1 of 1)

- [Progressive Alignment Objectives for Aligner-Encoder based ASR](https://mlsanity.com/paper/2606.24147/) (2026)

## Abstract (arXiv)

Modern systems for automatic speech recognition, including the RNN-Transducer and Attention-based Encoder-Decoder (AED), are designed so that the encoder is not required to alter the time-position of information from the audio sequence into the embedding; alignment to the final text output is processed during decoding. We discover that the transformer-based encoder adopted in recent years is actually capable of performing the alignment internally during the forward pass, prior to decoding. This new phenomenon enables a simpler and more efficient model, the "Aligner-Encoder". To train it, we discard the dynamic programming of RNN-T in favor of the frame-wise cross-entropy loss of AED, while the decoder employs the lighter text-only recurrence of RNN-T without learned cross-attention -- it simply scans embedding frames in order from the beginning, producing one token each until predicting the end-of-message. We conduct experiments demonstrating performance remarkably close to the state of the art, including a special inference configuration enabling long-form recognition. In a representative comparison, we measure the total inference time for our model to be 2x faster than RNN-T and 16x faster than AED. Lastly, we find that the audio-text alignment is clearly visible in the self-attention weights of a certain layer, which could be said to perform "self-transduction".