Random Utterance Concatenation Based Data Augmentation for Improving Short-video Speech Recognition
Not on the map. Why?
Abstract (arXiv)
One of limitations in end-to-end automatic speech recognition (ASR) framework is its performance would be compromised if train-test utterance lengths are mismatched. In this paper, we propose an on-the-fly random utterance concatenation (RUC) based data augmentation method to alleviate train-test utterance length mismatch issue for short-video ASR task. Specifically, we are motivated by observations that our human-transcribed training utterances tend to be much shorter for short-video spontaneous speech (~3 seconds on average), while our test utterance generated from voice activity detection front-end is much longer (~10 seconds on average). Such a mismatch can lead to suboptimal performance. Empirically, it's observed the proposed RUC method significantly improves long utterance recognition without performance drop on short one. Overall, it achieves 5.72% word error rate reduction on average for 15 languages and improved robustness to various utterance length.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 28 of its 36 references that are in the map. First posted on arXiv 28 Oct 2022.
Builds on
28 of 36 references.
References · 28
- 2017Attention Is All You Needcited by 59,932
- 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
- 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,973
- 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
- 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
- 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,471
- 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
- 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 779
- 2013Speech Recognition with Deep Recurrent Neural Networkscited by 666
- 2015Listen, Attend and Spellcited by 542
- 2015Attention-Based Models for Speech Recognitioncited by 400
- 2016Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learningcited by 254
16 more
- 2018Streaming End-to-end Speech Recognition For Mobile Devicescited by 230
- 2017State-of-the-art Speech Recognition With Sequence-to-Sequence Modelscited by 196
- 2015End-to-End Attention-based Large Vocabulary Speech Recognitioncited by 148
- 2020A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latencycited by 99
- 2019Recognizing long-form speech using streaming end-to-end modelscited by 77
- 2019Speech Recognition with Augmented Synthesized Speechcited by 60
- 2019A comparison of end-to-end models for long-form speech recognitioncited by 42
- 2020Using Synthetic Audio to Improve The Recognition of Out-Of-Vocabulary Words in End-To-End ASR Systemscited by 41
- 2019Improving sequence-to-sequence speech recognition training with on-the-fly data augmentationcited by 29
- 2020RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutionscited by 26
- 2020Improving Tail Performance of a Deliberation E2E ASR Model Using a Large Text Corpuscited by 24
- 2019Improving Generalization of Transformer for Speech Recognition with Parallel Schedule Sampling and Relative Positional Embeddingcited by 12
- 2021Input Length Matters: Improving RNN-T and MWER Training for Long-form Telephony Speech Recognitioncited by 10
- 2022Internal Language Model Estimation Through Explicit Context Vector Learning for Attention-based Encoder-decoder ASRcited by 9
- 2022A Language Agnostic Multilingual Streaming On-Device ASR Systemcited by 9
- 2021Multi-Sentence Resampling: A Simple Approach to Alleviate Dataset Length Bias and Beam-Search Degradationcited by 4
Built on by
Citing papers per year: 2023: 2; 2024: 0; 2025: 0; 2026: 1.
3 papers.