activity
20182023
most citedQuantifying Bias in Automatic Speech Recognition

55 citations · 81 across the 12 of their papers we have counts for

collaborators

18 papers

cs.SD202312 cited

Efficient Neural Music Generation

Max W. Y. Lam, Qiao Tian, Tang Li +10

Recent progress in music generation has been remarkably advanced by the state-of-the-art MusicLM, which comprises a hierarchy of three LMs, respectively, for semantic, coarse acous…

eess.AS2023

Language-universal phonetic encoder for low-resource speech recognition

Siyuan Feng, Ming Tu, Rui Xia +2

Multilingual training is effective in improving low-resource ASR, which may partially be explained by phonetic representation sharing between languages. In end-to-end (E2E) ASR sys…

eess.AS2023

Language-Universal Phonetic Representation in Multilingual Speech Pretraining for Low-Resource Speech Recognition

Siyuan Feng, Ming Tu, Rui Xia +2

We improve low-resource ASR by integrating the ideas of multilingual training and self-supervised learning. Concretely, we leverage an International Phonetic Alphabet (IPA) multili…

cs.SD2022

Discovering Phonetic Inventories with Crosslingual Automatic Speech Recognition

Piotr Żelasko, Siyuan Feng, Laureano Moro Velazquez +5

The high cost of data acquisition makes Automatic Speech Recognition (ASR) model training problematic for most existing languages, including languages that do not even have a writt…

cs.SD2022

The Effectiveness of Time Stretching for Enhancing Dysarthric Speech for Improved Dysarthric Speech Recognition

Luke Prananta, Bence Mark Halpern, Siyuan Feng +1

In this paper, we investigate several existing and a new state-of-the-art generative adversarial network-based (GAN) voice conversion method for enhancing dysarthric speech for imp…

eess.AS2021

Unsupervised Acoustic Unit Discovery by Leveraging a Language-Independent Subword Discriminative Feature Representation

Siyuan Feng, Piotr Żelasko, Laureano Moro-Velázquez +1

This paper tackles automatically discovering phone-like acoustic units (AUD) from unlabeled speech data. Past studies usually proposed single-step approaches. We propose a two-stag…