The reviewed record of science sign in
Pith

arxiv: 2005.09267 · v2 · pith:6O2UVR42 · submitted 2020-05-19 · cs.CL · cs.SD· eess.AS

Iterative Pseudo-Labeling for Speech Recognition

Qiantong Xu , Tatiana Likhomanenko , Jacob Kahn , Awni Hannun , Gabriel Synnaeve , Ronan Collobert This is my paper

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:6O2UVR42record.jsonopen to challenge →

classification cs.CL cs.SDeess.AS
keywords datapseudo-labelingmodeliterativelanguagelibrispeechlow-resourcerecognition
0
0 comments X
read the original abstract

Pseudo-labeling has recently shown promise in end-to-end automatic speech recognition (ASR). We study Iterative Pseudo-Labeling (IPL), a semi-supervised algorithm which efficiently performs multiple iterations of pseudo-labeling on unlabeled data as the acoustic model evolves. In particular, IPL fine-tunes an existing model at each iteration using both labeled data and a subset of unlabeled data. We study the main components of IPL: decoding with a language model and data augmentation. We then demonstrate the effectiveness of IPL by achieving state-of-the-art word-error rate on the Librispeech test sets in both standard and low-resource setting. We also study the effect of language models trained on different corpora to show IPL can effectively utilize additional text. Finally, we release a new large in-domain text corpus which does not overlap with the Librispeech training transcriptions to foster research in low-resource, semi-supervised ASR

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 3 Pith papers

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

  1. Emerging Properties in Self-Supervised Vision Transformers

    cs.CV 2021-04 conditional novelty 8.0

    Self-supervised ViTs show emergent semantic segmentation and 78.3% k-NN accuracy on ImageNet; DINO reaches 80.1% linear evaluation with ViT-Base.

  2. Vision Transformers Need Registers

    cs.CV 2023-09 unverdicted novelty 6.0

    Adding register tokens to Vision Transformers eliminates high-norm background artifacts and raises state-of-the-art performance on dense visual prediction tasks.

  3. Progressive Refinement: An Iterative Pseudo-Labeling Approach for Mandarin-English Code-Switching ASR

    cs.CL 2026-07 conditional novelty 4.0

    Iterative pseudo-labeling on 22.4k hours of unlabeled code-switching audio reduces Mix Error Rate on SEAME devman to 12.88% and devsge to 18.89%.