Pushing the performances of ASR models on English and Spanish accents
Not on the map. Why?
Abstract (arXiv)
Speech to text models tend to be trained and evaluated against a single target accent. This is especially true for English for which native speakers from the United States became the main benchmark. In this work, we are going to show how two simple methods: pre-trained embeddings and auxiliary classification losses can improve the performance of ASR systems. We are looking for upgrades as universal as possible and therefore we will explore their impact on several models architectures and several languages.
Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Builds on 18 of its 22 references that are in the map. First posted on arXiv 22 Dec 2022.
Builds on
18 of 22 references.
References · 18
- 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,870
- 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,979
- 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,366
- 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,359
- 2020Unsupervised Cross-lingual Representation Learning for Speech Recognitioncited by 500
- 2021VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretationcited by 456
- 2019Self-Training for End-to-End Speech Recognitioncited by 128
- 2020Emformer: Efficient Memory Transformer Based Acoustic Model For Low Latency Streaming Speech Recognitioncited by 111
- 2020Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameterscited by 110
- 2020Rethinking Evaluation in ASR: Are Our Models Robust Enough?cited by 72
- 2021Joint Unsupervised and Supervised Training for Multilingual ASRcited by 39
- 2020Streaming Transformer-based Acoustic Models Using Self-attention with Augmented Memorycited by 35
6 more
- 2020Improving RNN Transducer Based ASR with Auxiliary Taskscited by 27
- 2020Joint Masked CPC and CTC Training for ASRcited by 20
- 2018Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognitioncited by 14
- 2021ASR4REAL: An extended benchmark for speech modelscited by 14
- 2021Accent-Robust Automatic Speech Recognition Using Supervised and Unsupervised Wav2vec Embeddingscited by 12
- 2020NISP: A Multi-lingual Multi-accent Dataset for Speaker Profilingcited by 7
Built on by
Citing papers per year: 2026: 1.
1 paper.