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 method to improve ASR models for agglutinative and low-resource languages. This novel data augmentation method generates both synthetic text and synthetic audio. Some experiments were conducted using the corpus of the Quechua language, which is an agglutinative and low-resource language. In this study, a sequence-to-sequence (seq2seq) model was applied to generate synthetic text, in addition to generating synthetic speech using a text-to-speech (TTS) model for Quechua. The results show that the new data augmentation method works well to improve the ASR model for Quechua. In this research, an 8.73% improvement in the word-error-rate (WER) of the ASR model is obtained using a combination of synthetic text and synthetic speech.

📄 PDF Abstract BibTeX arXiv:2204.00291

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Data Augmentation speech-recognition Speech Recognition text-to-speech Text to Speech

MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognition

2021-02-25 · Linghui Meng, Jin Xu, Xu Tan, Jindong Wang 외

In this paper, we propose MixSpeech, a simple yet effective data augmentation method based on mixup for automatic speech recognition (ASR). MixSpeech trains an ASR model by taking a weighted combination of two different …

Automatic Speech Recognition Automatic Speech Recognition (ASR)Data Augmentation speech-recognition+1

Speech Synthesis as Augmentation for Low-Resource ASR

2020-12-23 · Deblin Bagchi, Shannon Wotherspoon, Zhuolin Jiang, Prasanna Muthukumar

Speech synthesis might hold the key to low-resource speech recognition. Data augmentation techniques have become an essential part of modern speech recognition training. Yet, they are simple, naive, and rarely reflect re…

Data Augmentation speech-recognition Speech Recognition Speech Synthesis

Cross-Speaker Emotion Transfer for Low-Resource Text-to-Speech Using Non-Parallel Voice Conversion with Pitch-Shift Data Augmentation

2022-04-21 · Ryo Terashima, Ryuichi Yamamoto, Eunwoo Song, Yuma Shirahata 외

Data augmentation via voice conversion (VC) has been successfully applied to low-resource expressive text-to-speech (TTS) when only neutral data for the target speaker are available. Although the quality of VC is crucial…

Data Augmentation text-to-speech Text to Speech Voice Conversion

You Do Not Need More Data: Improving End-To-End Speech Recognition by Text-To-Speech Data Augmentation

2020-05-14 · Aleksandr Laptev, Roman Korostik, Aleksey Svischev, Andrei Andrusenko 외

Data augmentation is one of the most effective ways to make end-to-end automatic speech recognition (ASR) perform close to the conventional hybrid approach, especially when dealing with low-resource tasks. Using recent a…

Automatic Speech Recognition Automatic Speech Recognition (ASR)Data Augmentation Language Modeling+6

Distribution augmentation for low-resource expressive text-to-speech

2022-02-13 · Mateusz Lajszczak, Animesh Prasad, Arent van Korlaar, Bajibabu Bollepalli 외

This paper presents a novel data augmentation technique for text-to-speech (TTS), that allows to generate new (text, audio) training examples without requiring any additional data. Our goal is to increase diversity of te…

Data Augmentation Diversity text-to-speech Text to Speech