Zirun Zhu

2021

A researcher in the Science corpus: 1 paper; trusts 0 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Papers from Zirun Zhu's perspective

Ordered by how strongly the researchers Zirun Zhu trusts endorse each paper. Same corpus, a different order for every researcher.

1. Librispeech: An ASR corpus based on public domain audio books
2. Audio Set: An ontology and human-labeled dataset for audio events
3. Listen, attend and spell: A neural network for large vocabulary conversational speech recognition
4. PyTorch: An Imperative Style, High-Performance Deep Learning Library
5. Speech Enhancement with LSTM Recurrent Neural Networks and its Application to Noise-Robust ASR
6. SEGAN: Speech Enhancement Generative Adversarial Network
7. Towards Better Decoding and Language Model Integration in Sequence to Sequence Models
8. Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs
9. Deep Complex Networks
10. Freesound Datasets: A Platform for the Creation of Open Audio Datasets

Their papers

• Human Listening and Live Captioning: Multi-Task Training for Speech Enhancement (2021) — 28 citations