3 papers
eess.AS2023
Single-channel speech enhancement using learnable loss mixup
Oscar Chang, Dung N. Tran, Kazuhito Koishida
Generalization remains a major problem in supervised learning of single-channel speech enhancement. In this work, we propose learnable loss mixup (LLM), a simple and effortless tra…
eess.AS2023
On Robustness to Missing Video for Audiovisual Speech Recognition
Oscar Chang, Otavio Braga, Hank Liao +2
It has been shown that learning audiovisual features can lead to improved speech recognition performance over audio-only features, especially for noisy speech. However, in many com…
eess.AS2023
Revisiting the Entropy Semiring for Neural Speech Recognition
Oscar Chang, Dongseong Hwang, Olivier Siohan
In streaming settings, speech recognition models have to map sub-sequences of speech to text before the full audio stream becomes available. However, since alignment information be…