Aku Rouhe

661 total citations
14 papers, 66 citations indexed

About

Aku Rouhe is a scholar working on Artificial Intelligence, Signal Processing and Computer Vision and Pattern Recognition. According to data from OpenAlex, Aku Rouhe has authored 14 papers receiving a total of 66 indexed citations (citations by other indexed papers that have themselves been cited), including 12 papers in Artificial Intelligence, 4 papers in Signal Processing and 2 papers in Computer Vision and Pattern Recognition. Recurrent topics in Aku Rouhe's work include Speech Recognition and Synthesis (8 papers), Natural Language Processing Techniques (7 papers) and Topic Modeling (6 papers). Aku Rouhe is often cited by papers focused on Speech Recognition and Synthesis (8 papers), Natural Language Processing Techniques (7 papers) and Topic Modeling (6 papers). Aku Rouhe collaborates with scholars based in Finland, United States and Denmark. Aku Rouhe's co-authors include Mikko Kurimo, Stig-Arne Grönroos, Lucia Specia, Ozan Çağlayan, Desmond Elliott, Jörg Tiedemann, Umut Sulubacak, Tamás Grósz, Hemant Kumar Kathania and Juho Leinonen and has published in prestigious journals such as Language Resources and Evaluation, IEEE/ACM Transactions on Audio Speech and Language Processing and Machine Translation.

In The Last Decade

Aku Rouhe

12 papers receiving 63 citations

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name	h						Papers	Cites
Aku Rouhe Finland	4	55	17	17	4	4	14	66
Daan van Esch United States	8	78 1.4×	6 0.4×	13 0.8×	5 1.3×	6 1.5×	12	84
Simran Khanuja United States	5	97 1.8×	6 0.4×	21 1.2×	2 0.5×	3 0.8×	8	109
Sabrina J. Mielke United States	5	61 1.1×	12 0.7×	7 0.4×		3 0.8×	5	67
Quchen Fu United States	5	33 0.6×	20 1.2×	30 1.8×	2 0.5×		8	62
Kaizhao Liang United States	3	35 0.6×	24 1.4×	7 0.4×	2 0.5×		4	49
Shuoyang Ding United States	7	127 2.3×	34 2.0×	29 1.7×	2 0.5×	3 0.8×	12	134
Dmitriy Serdyuk United States	6	59 1.1×	25 1.5×	64 3.8×	3 0.8×		7	90
Ramon Sanabria United Kingdom	6	102 1.9×	20 1.2×	29 1.7×	2 0.5×	1 0.3×	11	116
Houssem Maghrebi France	5	40 0.7×	16 0.9×	12 0.7×			7	41
Guillaume Wisniewski France	8	155 2.8×	18 1.1×	11 0.6×	4 1.0×	2 0.5×	40	162

Countries citing papers authored by Aku Rouhe

Since Specialization

Citations

This map shows the geographic impact of Aku Rouhe'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 Aku Rouhe with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Aku Rouhe more than expected).

Fields of papers citing papers by Aku Rouhe

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Aku Rouhe. 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 Aku Rouhe. The network helps show where Aku Rouhe may publish in the future.

Co-authorship network of co-authors of Aku Rouhe

This figure shows the co-authorship network connecting the top 25 collaborators of Aku Rouhe. A scholar is included among the top collaborators of Aku Rouhe based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Aku Rouhe. Aku Rouhe is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

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

14 of 14 papers shown

Rouhe, Aku, Tamás Grósz, & Mikko Kurimo. (2023). Principled Comparisons for End-to-End Speech Recognition: Attention vs Hybrid at the 1000-Hour Scale. IEEE/ACM Transactions on Audio Speech and Language Processing. 32. 623–638. 2 indexed citations

Rouhe, Aku, et al.. (2023). Finnish parliament ASR corpus. Language Resources and Evaluation. 57(4). 1645–1670. 4 indexed citations

Grósz, Tamás, et al.. (2023). Investigating wav2vec2 context representations and the effects of fine-tuning, a case-study of a Finnish model. Aaltodoc (Aalto University). 196–200.

Rouhe, Aku, et al.. (2022). Low Resource Comparison of Attention-based and Hybrid ASR Exploiting wav2vec 2.0. Interspeech 2022. 3543–3547. 4 indexed citations

Rouhe, Aku, Stig-Arne Grönroos, Sámi Virpioja, Mathias Creutz, & Mikko Kurimo. (2022). Morfessor-enriched features and multilingual training for canonical morphological segmentation. Aaltodoc (Aalto University). 144–151. 2 indexed citations

Kathania, Hemant Kumar, et al.. (2021). Speaker Verification Experiments for Adults and Children Using Shared Embedding Spaces. Aaltodoc (Aalto University). 86–93. 2 indexed citations

Rouhe, Aku, et al.. (2021). Self-Supervised End-to-End ASR for Low Resource L2 Swedish. Aaltodoc (Aalto University). 1429–1433. 10 indexed citations

Rouhe, Aku, et al.. (2020). Speaker-Aware Training of Attention-Based End-to-End Speech Recognition Using Neural Speaker Embeddings. Aaltodoc (Aalto University). 7064–7068. 1 indexed citations

Sulubacak, Umut, Ozan Çağlayan, Stig-Arne Grönroos, et al.. (2020). Multimodal machine translation through visuals and speech. Machine Translation. 34(2-3). 97–147. 34 indexed citations

10.

Rouhe, Aku, et al.. (2020). Finnish ASR with Deep Transformer Models. Aaltodoc (Aalto University). 3630–3634. 2 indexed citations

11.

Rouhe, Aku, et al.. (2019). Spherediar: An Effective Speaker Diarization System for Meeting Data. Aaltodoc (Aalto University). 12. 373–380. 1 indexed citations

12.

Sulubacak, Umut, Ozan Çağlayan, Stig-Arne Grönroos, et al.. (2019). Multimodal Machine Translation through Visuals and Speech. Zenodo (CERN European Organization for Nuclear Research). 2 indexed citations

13.

Sulubacak, Umut, Jörg Tiedemann, Aku Rouhe, Stig-Arne Grönroos, & Mikko Kurimo. (2018). The MeMAD Submission to the IWSLT 2018 Speech Translation Task. arXiv (Cornell University). 89–94. 1 indexed citations

14.

Rouhe, Aku, Reima Karhila, Peter Smit, & Mikko Kurimo. (2017). Reading validation for pronunciation evaluation in the Digitala project. Aaltodoc (Aalto University). 1 indexed citations

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