Text Augmentation for Language Models in High Error Recognition Scenario

2020-11-11 · Karel Beneš, Lukáš Burget

We examine the effect of data augmentation for training of language models for speech recognition. We compare augmentation based on global error statistics with one based on per-word unigram statistics of ASR errors and observe that it is better to only pay attention the global substitution, deletion and insertion rates. This simple scheme also performs consistently better than label smoothing and its sampled variants. Additionally, we investigate into the behavior of perplexity estimated on augmented data, but conclude that it gives no better prediction of the final error rate. Our best augmentation scheme increases the absolute WER improvement from second-pass rescoring from 1.1 % to 1.9 % absolute on the CHiMe-6 challenge.

📄 PDF Abstract BibTeX arXiv:2011.06056

Code (1)

BUTSpeechFIT/BrnoLM 공식 구현 pytorch

Tasks

Data Augmentation speech-recognition Speech RecognitionText AugmentationVocal Bursts Intensity Prediction

Methods 이 논문이 사용한 방법론

Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Text-To-Speech Data Augmentation for Low Resource Speech Recognition

2022-04-01 · Rodolfo Zevallos

Nowadays, the main problem of deep learning techniques used in the development of automatic speech recognition (ASR) models is the lack of transcribed data. The goal of this research is to propose a new data augmentation…

Automatic Speech Recognition Automatic Speech Recognition (ASR)Data Augmentation speech-recognition+3

Semi-supervised transfer learning for language expansion of end-to-end speech recognition models to low-resource languages

2021-11-19 · Jiyeon Kim, Mehul Kumar, Dhananjaya Gowda, Abhinav Garg 외

In this paper, we propose a three-stage training methodology to improve the speech recognition accuracy of low-resource languages. We explore and propose an effective combination of techniques such as transfer learning, …

Data Augmentation speech-recognition Speech Recognition text-to-speech+2

Data Augmentation for Training Dialog Models Robust to Speech Recognition Errors

2020-06-10 · WS 2020 7 · Longshaokan Wang, Maryam Fazel-Zarandi, Aditya Tiwari, Spyros Matsoukas 외

Speech-based virtual assistants, such as Amazon Alexa, Google assistant, and Apple Siri, typically convert users' audio signals to text data through automatic speech recognition (ASR) and feed the text to downstream dial…

Automatic Speech Recognition Automatic Speech Recognition (ASR)Data Augmentation Natural Language Understanding+3

Analyzing ASR pretraining for low-resource speech-to-text translation

2019-10-23 · Mihaela C. Stoian, Sameer Bansal, Sharon Goldwater

Previous work has shown that for low-resource source languages, automatic speech-to-text translation (AST) can be improved by pretraining an end-to-end model on automatic speech recognition (ASR) data from a high-resourc…

Automatic Speech Recognition Automatic Speech Recognition (ASR)Data Augmentation speech-recognition+4

Handwritten text generation and strikethrough characters augmentation

2021-12-14 · Alex Shonenkov, Denis Karachev, Max Novopoltsev, Mark Potanin 외

We introduce two data augmentation techniques, which, used with a Resnet-BiLSTM-CTC network, significantly reduce Word Error Rate (WER) and Character Error Rate (CER) beyond best-reported results on handwriting text reco…

Data Augmentation HTR Text Generation