Papers › Multi-blank Transducers for Speech Recognition

Multi-blank Transducers for Speech Recognition

4 Nov 2022arXiv:2211.03541archive 2025-07-28

Hainan Xu, Fei Jia, Somshubra Majumdar, Shinji Watanabe, Boris Ginsburg

This paper proposes a modification to RNN-Transducer (RNN-T) models for automatic speech recognition (ASR). In standard RNN-T, the emission of a blank symbol consumes exactly one input frame; in our proposed method, we introduce additional blank symbols, which consume two or more input frames when emitted. We refer to the added symbols as big blanks, and the method multi-blank RNN-T. For training multi-blank RNN-Ts, we propose a novel logit under-normalization method in order to prioritize emissions of big blanks. With experiments on multiple languages and datasets, we show that multi-blank RNN-T methods could bring relative speedups of over +90%/+139% to model inference for English Librispeech and German Multilingual Librispeech datasets, respectively. The multi-blank RNN-T method also improves ASR accuracy consistently. We will release our implementation of the method in the NeMo (https://github.com/NVIDIA/NeMo) toolkit.

PaperPDFCode

Code

NVIDIA/NeMo officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
chimechallenge/C8DASR-Baseline-NeMo mentioned on GitHubpytorchApache-2.0 report
kehanlu/Nemo mentioned on GitHubpytorchApache-2.0 report
wd929/NeMo mentioned on GitHubpytorchApache-2.0 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)Speech Recognitionspeech-recognition

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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