# An Investigation of Monotonic Transducers for Large-Scale Automatic Speech Recognition

arXiv: https://arxiv.org/abs/2204.08858 · HTML: https://mlsanity.com/paper/2204.08858/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Apr 2022.

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

- [A Token-Wise Beam Search Algorithm for RNN-T](https://mlsanity.com/paper/2302.14357/) (2023)
- [Boosting Hybrid Autoregressive Transducer-based ASR with Internal Acoustic Model Training and Dual Blank Thresholding](https://mlsanity.com/paper/2409.20313/) (2024)

## Abstract (arXiv)

The two most popular loss functions for streaming end-to-end automatic speech recognition (ASR) are RNN-Transducer (RNN-T) and connectionist temporal classification (CTC). Between these two loss types we can classify the monotonic RNN-T (MonoRNN-T) and the recently proposed CTC-like Transducer (CTC-T). Monotonic transducers have a few advantages. First, RNN-T can suffer from runaway hallucination, where a model keeps emitting non-blank symbols without advancing in time. Secondly, monotonic transducers consume exactly one model score per time step and are therefore more compatible with traditional FST-based ASR decoders. However, the MonoRNN-T so far has been found to have worse accuracy than RNN-T. It does not have to be that way: By regularizing the training via joint LAS training or parameter initialization from RNN-T, both MonoRNN-T and CTC-T perform as well or better than RNN-T. This is demonstrated for LibriSpeech and for a large-scale in-house data set.