Papers › Memory-augmented conformer for improved end-to-end long-form ASR

Memory-augmented conformer for improved end-to-end long-form ASR

22 Sep 2023arXiv:2309.13029archive 2025-07-28

Carlos Carvalho, Alberto Abad

Conformers have recently been proposed as a promising modelling approach for automatic speech recognition (ASR), outperforming recurrent neural network-based approaches and transformers. Nevertheless, in general, the performance of these end-to-end models, especially attention-based models, is particularly degraded in the case of long utterances. To address this limitation, we propose adding a fully-differentiable memory-augmented neural network between the encoder and decoder of a conformer. This external memory can enrich the generalization for longer utterances since it allows the system to store and retrieve more information recurrently. Notably, we explore the neural Turing machine (NTM) that results in our proposed Conformer-NTM model architecture for ASR. Experimental results using Librispeech train-clean-100 and train-960 sets show that the proposed system outperforms the baseline conformer without memory for long utterances.

PaperPDFCode

Code

miamoto/conformer-ntm officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DecoderFormSpeech Recognitionspeech-recognition

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Content-based AttentionLSTMLocation-based AttentionNeural Turing MachineSigmoid ActivationSoftmaxTanh Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections