Ashkan Aazami

Signal Processing · 2020–2023

A researcher in the Science corpus: 3 papers; trusts 1 researcher and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Signal Processing — 51 citations into it

Whom Ashkan Aazami trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Chandan K. A. Reddy

Papers from Ashkan Aazami's perspective

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

1. Audio Set: An ontology and human-labeled dataset for audio events
2. Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
3. A Regression Approach to Speech Enhancement Based on Deep Neural Networks
4. Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs
5. Librispeech: An ASR corpus based on public domain audio books
6. The Diverse Environments Multi-channel Acoustic Noise Database (DEMAND): A database of multichannel environmental noise recordings
7. The Weizmann Institute of Science
8. A Hybrid DSP/Deep Learning Approach to Real-Time Full-Band Speech Enhancement
9. Image method for efficiently simulating small‐room acoustics
10. ViSQOL: an objective speech quality model

Their papers

• The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Results (2020) — 460 citations
• ICASSP 2023 Deep Noise Suppression Challenge (2023) — 193 citations
• The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Speech Quality and Testing Framework (2020) — 91 citations