RedApt: An Adaptor for wav2vec 2 Encoding Faster and Smaller Speech Translation without Quality Compromise
Not on the map. Why?
Abstract (arXiv)
Pre-trained speech Transformers in speech translation (ST) have facilitated state-of-the-art (SotA) results; yet, using such encoders is computationally expensive. To improve this, we present a novel Reducer Adaptor block, RedApt, that could be seamlessly integrated within any Transformer-based speech encoding architecture. Integrating the pretrained wav2vec 2 speech encoder with RedAptbrings 41% speedup, 33% memory reduction with 24% fewer FLOPs at inference. To our positive surprise, our ST model with RedApt outperforms the SotA architecture by an average of 0.68 BLEU score on 8 language pairs from Must-C.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 20 of its 28 references that are in the map. First posted on arXiv 16 Oct 2022.
Builds on
20 of 28 references.
References · 20
- 2017Attention Is All You Needcited by 59,932
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
- 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
- 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,486
- 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,028
- 2021SUPERB: Speech processing Universal PERformance Benchmarkcited by 652
- 2020Multilingual Translation with Extensible Multilingual Pretraining and Finetuningcited by 287
- 2020fairseq S2T: Fast Speech-to-Text Modeling with fairseqcited by 174
- 2020Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processingcited by 161
- 2021DistilHuBERT: Speech Representation Learning by Layer-wise Distillation of Hidden-unit BERTcited by 129
- 2021Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognitioncited by 68
8 more
- 2021PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognitioncited by 50
- 2021End-to-end Speech Translation via Cross-modal Progressive Trainingcited by 47
- 2021CTC-based Compression for Direct Speech Translationcited by 45
- 2020Adaptive Feature Selection for End-to-End Speech Translationcited by 25
- 2021Shrinking Bigfoot: Reducing wav2vec 2.0 footprintcited by 16
- 2021End-to-End Speech Translation with Pre-trained Models and Adapters: UPC at IWSLT 2021cited by 16
- 2022M-Adapter: Modality Adaptation for End-to-End Speech-to-Text Translationcited by 15
- 2020Phone Features Improve Speech Translationcited by 11
Built on by
Citing papers per year: 2024: 2.
2 papers.