Transfer learning for speech and language processing
Transfer learning is a vital technique that generalizes models trained for one setting or task
to other settings or tasks. For example in speech recognition, an acoustic model trained for …
to other settings or tasks. For example in speech recognition, an acoustic model trained for …
Unsupervised speech representation learning using wavenet autoencoders
We consider the task of unsupervised extraction of meaningful latent representations of
speech by applying autoencoding neural networks to speech waveforms. The goal is to …
speech by applying autoencoding neural networks to speech waveforms. The goal is to …
Unsupervised pretraining transfers well across languages
Cross-lingual and multi-lingual training of Automatic Speech Recognition (ASR) has been
extensively investigated in the supervised setting. This assumes the existence of a parallel …
extensively investigated in the supervised setting. This assumes the existence of a parallel …
A survey on automatic speech recognition systems for Portuguese language and its variations
TA de Lima, M Da Costa-Abreu - Computer Speech & Language, 2020 - Elsevier
Communication has been an essential part of being human and living in society. There are
several different languages and variations of them, so you can speak English in one place …
several different languages and variations of them, so you can speak English in one place …
Automatic speech recognition for under-resourced languages: A survey
Speech processing for under-resourced languages is an active field of research, which has
experienced significant progress during the past decade. We propose, in this paper, a …
experienced significant progress during the past decade. We propose, in this paper, a …
Libri-light: A benchmark for asr with limited or no supervision
We introduce a new collection of spoken English audio suitable for training speech
recognition systems under limited or no supervision. It is derived from open-source audio …
recognition systems under limited or no supervision. It is derived from open-source audio …
Language independent end-to-end architecture for joint language identification and speech recognition
End-to-end automatic speech recognition (ASR) can significantly reduce the burden of
developing ASR systems for new languages, by eliminating the need for linguistic …
developing ASR systems for new languages, by eliminating the need for linguistic …
Multilingual end-to-end speech translation
In this paper, we propose a simple yet effective framework for multilingual end-to-end
speech translation (ST), in which speech utterances in source languages are directly …
speech translation (ST), in which speech utterances in source languages are directly …
Data augmentation for low resource languages
Recently there has been interest in the approaches for training speech recognition systems
for languages with limited resources. Under the IARPA Babel program such resources have …
for languages with limited resources. Under the IARPA Babel program such resources have …
Sequence-based multi-lingual low resource speech recognition
Techniques for multi-lingual and cross-lingual speech recognition can help in low resource
scenarios, to bootstrap systems and enable analysis of new languages and domains. End-to …
scenarios, to bootstrap systems and enable analysis of new languages and domains. End-to …