Mahsa Arab Yarmohammadi

Artificial Intelligence · 2018–2025

A researcher in the Science corpus: 2 papers; trusts 3 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 37 citations into it
• Signal Processing — 7 citations into it
• Speech & Audio — 6 citations into it

Whom Mahsa Arab Yarmohammadi trusts

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

1. Sanjeev Khudanpur (in Artificial Intelligence)
2. Daniel Povey (in Artificial Intelligence)
3. Vijayaditya Peddinti (in Artificial Intelligence)

Papers from Mahsa Arab Yarmohammadi's perspective

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

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. Understanding the difficulty of training deep feedforward neural networks
3. The Kaldi Speech Recognition Toolkit
4. Audio augmentation for speech recognition
5. Training Very Deep Networks
6. Highway long short-term memory RNNS for distant speech recognition
7. Restructuring of deep neural network acoustic models with singular value decomposition
8. On the compression of recurrent neural networks with an application to LVCSR acoustic modeling for embedded speech recognition
9. Purely Sequence-Trained Neural Networks for ASR Based on Lattice-Free MMI
10. Low Latency Acoustic Modeling Using Temporal Convolution and LSTMs

Their papers

• Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks (2018) — 522 citations
• mFollowIR: a Multilingual Benchmark for Instruction Following in Retrieval (2025)