Voice Conversion Can Improve ASR in Very Low-Resource Settings

Domain:

natural language processing

Record type:

paper

Creator:

BaaKam

Host:

Voice conversion (VC) could be used to improve speech recognition systems in low-resource languages by using it to augment limited training data. However, VC has not been widely used for this purpose because of practical issues such as compute speed and limitations when converting to and from unseen speakers. Moreover, it is still unclear whether a VC model trained on one well-resourced language can be applied to speech from another low-resource language for the aim of data augmentation. In this work we assess whether a VC system can be used cross-lingually to improve low-resource speech recognition. We combine several recent techniques to design and train a practical VC system in English, and then use this system to augment data for training speech recognition models in several low-resource languages. When using a sensible amount of VC augmented data, speech recognition performance is improved in all four low-resource languages considered. We also show that VC-based augmentation is superior to SpecAugment (a widely used signal processing augmentation method) in the low-resource languages considered. 5 page, 4 tables, 2 figures. Accepted at Interspeech 2022

Visit

arxiv.org

Tasks

automatic speech recognition speech processing

ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversion

We explore cross-lingual multi-speaker speech synthesis and cross-lingual voice conversion applied t

Towards Inclusive ASR: Investigating Voice Conversion for Dysarthric Speech Recognition in Low-Resource Languages

Automatic speech recognition (ASR) for dysarthric speech remains challenging due to data scarcity, p

Finetuning Pretrained Model with Embedding of Domain and Language Information for ASR of Very Low-Resource Settings

This study investigates the effective incorporation of meta-information such as domain and language

Spoken Term Detection Methods for Sparse Transcription in Very Low-resource Settings

We investigate the efficiency of two very different spoken term detection approaches for transcripti

Can Linguistically Related Languages Guide LLM Translation in Low-Resource Settings?

Large Language Models (LLMs) have achieved strong performance across many downstream tasks, yet thei

Doppler ultrasound to improve prediction of adverse perinatal outcomes in low resource settings

Chapter 1 provides the general background for the thesis, providing an overview of the global burden