The reviewed record of science sign in
Pith

arxiv: 2106.05642 · v3 · pith:V43UYKEY · submitted 2021-06-10 · cs.SD · cs.CL· eess.AS

U2++: Unified Two-pass Bidirectional End-to-end Model for Speech Recognition

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:V43UYKEYrecord.jsonopen to challenge →

classification cs.SD cs.CLeess.AS
keywords streamingmodelrecognitionaccuracyaccurateaishell-1backwarddecoding
0
0 comments X
read the original abstract

The unified streaming and non-streaming two-pass (U2) end-to-end model for speech recognition has shown great performance in terms of streaming capability, accuracy, real-time factor (RTF), and latency. In this paper, we present U2++, an enhanced version of U2 to further improve the accuracy. The core idea of U2++ is to use the forward and the backward information of the labeling sequences at the same time at training to learn richer information, and combine the forward and backward prediction at decoding to give more accurate recognition results. We also proposed a new data augmentation method called SpecSub to help the U2++ model to be more accurate and robust. Our experiments show that, compared with U2, U2++ shows faster convergence at training, better robustness to the decoding method, as well as consistent 5\% - 8\% word error rate reduction gain over U2. On the experiment of AISHELL-1, we achieve a 4.63\% character error rate (CER) with a non-streaming setup and 5.05\% with a streaming setup with 320ms latency by U2++. To the best of our knowledge, 5.05\% is the best-published streaming result on the AISHELL-1 test set.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. IQRA 2026: Interspeech Challenge on Automatic Pronunciation Assessment for Modern Standard Arabic (MSA)

    cs.SD 2026-03 unverdicted novelty 5.0

    The IQRA 2026 challenge on Arabic mispronunciation detection reports a 0.28 F1-score gain from new authentic human error data and diverse modeling approaches including self-supervised and audio-language models.