Haşim Sak

9.5k citations

45 papers · 5.2k indexed · 3 hit papers · h-index 25

Impact in

Signal Processing top 0.2%
- Music and Audio Processing
- Speech and Audio Processing
Artificial Intelligence top 0.2%
- Speech Recognition and Synthesis
- Natural Language Processing Techniques
- Topic Modeling
- Speech and dialogue systems
- Anomaly Detection Techniques and Applications

Papers in

Signal Processing 23
- Speech and Audio Processing 20
- Music and Audio Processing 16
Artificial Intelligence 41
- Speech Recognition and Synthesis 38
- Natural Language Processing Techniques 23
- Topic Modeling 12
- Speech and dialogue systems 6

Co-authors: Andrew Senior Françoise Beaufays Tara N. Sainath Oriol Vinyals Kanishka Rao Heiga Zen Hagen Soltau Murat Saraçlar
Journals: IEEE Transactions on Audio Speech and Language Processing (2 papers)Language Resources and Evaluation (1 paper)Journal on Multimodal User Interfaces (1 paper)ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2 papers)Zenodo (CERN European Organization for Nuclear Research) (1 paper)
Partner nations: United States Türkiye Czechia

In The Last Decade

Haşim Sak

45 papers receiving 4.7k citations

Hit Papers

align trajectories log scale

Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss 2020 · 277 citations

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if any of the following hold:

it has ≥500 total citations;
it reaches ≥1.5× the top-1% citation threshold for papers in the same subfield and year (the threshold is the minimum needed to enter the top 1%, not the average within it);
it reaches the top citation threshold in at least one of its specific research topics.

2020 Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss
2015 Convolutional, Long Short-Term Memory, fully connected Deep Neural Networks
2014 Long short-term memory recurrent neural network architectures for large scale acoustic modeling

Peers

Countries citing papers authored by Haşim Sak

Since Specialization

Citations

This map shows the geographic impact of Haşim Sak's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Haşim Sak with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Haşim Sak more than expected).

Fields of papers citing papers by Haşim Sak

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Haşim Sak. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Haşim Sak. The network helps show where Haşim Sak may publish in the future.

Co-authorship network

The 25 scholars most cited alongside Haşim Sak, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.

Border = papers with Haşim Sak Line = papers co-authored together Haşim Sak links everyone, so they are left out of the graph.

All Works

Sort: Min cites: Since: Top N: Style:

20 of 20 papers shown

#	Work
1	Cross-Training: A Semi-Supervised Training Scheme for Speech Recognition In Ahn, Anshuman Tripathi, Jaeyoung Kim, Lu Han, Qian Zhang, Rohit Prabhavalkar, Haşim Sak	2023	2
2	Contrastive Siamese Network for Semi-Supervised Speech Recognition ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) ·In Ahn, Jaeyoung Kim, Anshuman Tripathi, Lu Han, Qian Zhang, Haşim Sak	2022	7
3	Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss Qian Zhang, Lu Han, Haşim Sak, Anshuman Tripathi, Erik McDermott, Dario Barni, Shankar Kumar Hit paper breakdown →	2020	277
4	End-To-End Multi-Talker Overlapping Speech Recognition Anshuman Tripathi, Lu Han, Haşim Sak	2020	28
5	Speech Recognition for Medical Conversations Chung‐Cheng Chiu, Anshuman Tripathi, Katherine Chou, Diana Marcela Fandiño Ulloa, Navdeep Jaitly, Christina Brinck, Anjuli Kannan, Patrick Nguyen, Haşim Sak, Ananth Sankar, J.-B. Chabot, Elif Evrim Ekin, Yonghui Wu, Xuedong Zhang	2018	41
6	Exploring architectures, data and units for streaming end-to-end speech recognition with RNN-transducer Kanishka Rao, Haşim Sak, Rohit Prabhavalkar	2017	193
7	Neural Speech Recognizer: Acoustic-to-Word LSTM Model for Large Vocabulary Speech Recognition Hagen Soltau, Hank Liao, Haşim Sak	2017	191
8	Multi-accent speech recognition with hierarchical grapheme based models Kanishka Rao, Haşim Sak	2017	43
9	Personalized speech recognition on mobile devices Ian McGraw, Rohit Prabhavalkar, Raziel Álvarez, Carole Wagnon, Kanishka Rao, David Rybach, Ouais Alsharif, Haşim Sak, Alexander Gruenstein, Françoise Beaufays, Carolina Parada	2016	97
10	Convolutional, Long Short-Term Memory, fully connected Deep Neural Networks Tara N. Sainath, Oriol Vinyals, Andrew Senior, Haşim Sak Hit paper breakdown →	2015	1080
11	Grapheme-to-phoneme conversion using Long Short-Term Memory recurrent neural networks Kanishka Rao, Fuchun Peng, Haşim Sak, Françoise Beaufays	2015	106
12	Acoustic modelling with CD-CTC-SMBR LSTM RNNS Andrew andrew, Haşim Sak, Félix de Chaumont Quitry, Tara N. Sainath, Kanishka Rao	2015	61
13	Learning acoustic frame labeling for speech recognition with recurrent neural networks Haşim Sak, Andrew Senior, Kanishka Rao, Ozan İrsoy, Alex Graves, Françoise Beaufays, Johan Schalkwyk	2015	100
14	Sequence discriminative distributed training of long short-term memory recurrent neural networks Haşim Sak, Oriol Vinyals, Georg Heigold, Andrew Senior, Erik McDermott, Rajat Monga, M. Mao	2014	96
15	Long short-term memory recurrent neural network architectures for large scale acoustic modeling Haşim Sak, Andrew Senior, Françoise Beaufays Hit paper breakdown →	2014	1943
16	Mixture of mixture n-gram language models Haşim Sak, Cyril Allauzen, Kosem Riam, Françoise Beaufays	2013	2
17	Discriminative reranking of ASR hypotheses with morpholexical and N-best-list features Haşim Sak, Murat Saraçlar, Tunga Güngör	2011	14
18	On-the-fly lattice rescoring for real-time automatic speech recognition Haşim Sak, Murat Saraçlar, Tunga Güngör	2010	19
19	Resources for Turkish morphological processing Language Resources and Evaluation ·Haşim Sak, Tunga Güngör, Murat Saraçlar	2010	39
20	A Corpus-Based Concatenative Speech Synthesis System for Turkish DergiPark (Istanbul University) ·Haşim Sak, Tunga Güngör, Ceren Altun	2006	22

About Haşim Sak

Haşim Sak is a scholar working on Signal Processing, Artificial Intelligence, Human-Computer Interaction, Computer Vision and Pattern Recognition and Ocean Engineering, having authored 45 papers that have together received 5.2k indexed citations. Recurring topics across this work include Speech Recognition and Synthesis (38 papers), Natural Language Processing Techniques (23 papers), Speech and Audio Processing (20 papers), Music and Audio Processing (16 papers), Topic Modeling (12 papers), Speech and dialogue systems (6 papers), Handwritten Text Recognition Techniques (3 papers) and Hand Gesture Recognition Systems (2 papers). The work is most often cited by research in Signal Processing (2.1k citations), Artificial Intelligence (3.4k citations), Computer Vision and Pattern Recognition (690 citations), Human-Computer Interaction (116 citations) and Experimental and Cognitive Psychology (207 citations). Haşim Sak has collaborated with scholars based in United States, Türkiye and Czechia. Frequent co-authors include Andrew Senior, Françoise Beaufays, Tara N. Sainath, Oriol Vinyals, Kanishka Rao, Heiga Zen, Hagen Soltau, Murat Saraçlar, Rohit Prabhavalkar and Anshuman Tripathi. Their work appears in journals such as IEEE Transactions on Audio Speech and Language Processing, Language Resources and Evaluation, Journal on Multimodal User Interfaces, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) and Zenodo (CERN European Organization for Nuclear Research).

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact