Deliverables
The first set of deliverables have been approved by the European Commission and are now accessible below. As soon as any additional deliverable is accepted, it will be made available for download as well. (Status as of July 1 2021)
Deliverable Number - Deliverable Title - Dissemination level - Due Date (in months)
D1.2 - Risk Assessment - Public - M6 
D1.4 - Internal progress and quality planning report Y1 - Public - M12
D1.5 - Internal progress and quality planning report Y2 - Public - M24
D1.6 - Final progress report - Public - M36
D3.1 - Initial report on compliance with ethical principles - Public - M12
D3.2 - Development of a decision-making- mechanism - Public - M14
D3.3 - INTERPOL global communications infrastructure - Public - M18
D3.4 - Final report on compliance with ethical principles - Public - M36
D4.1 - Overview and analysis of lawfully intercepted data - Public - M4
D4.2 - Simulated data for development and demonstration - Public - M16
D4.3 - Final report on ROXANNE data - Public - M30
D4.4 - ROXANNE case management and data preprocessing - Public - M32
D5.1 - Initial speech/text/video technologies - Public - M8
D5.2 - Interaction of speech/ text/video and network analysis - Public - M18
D5.3 - Final set of speech/text/ video technologies - Public - M33
D6.1 - Preliminary report on network analysis - Public - M9
D6.3 - Analysis of criminal networks - Public - M24
D6.4 - Systematic comparison of criminal networks - Public - M33
D7.1 - Technical specifications and detailed architecture - Public - M6
D7.2 - Description of the integration toolkit, guidelines, plan - Public - M9
D7.3 - Data visualization and exploratory analysis V1 - Public - M18
D7.4 - Description of ROXANNE platform V1, data export - Public - M20
D7.5 - Data visualization V2, ROXANNE platform V2 - Public - M32
D8.2 - Training manual Volume I - Public - M8
D8.7 - Training manual Volume II - Public - M19
D8.8 - Training manual Volume III - Public - M29
D9.1 - Creation of the project's identity and website - Public - M2
D9.2 - The project's communications plan - Public - M4
D9.3 - The project's dissemination and exploitation plan - Public - M5
D9.5 - Report on the dissemination, exploitation - Public - M18
D9.6 - Report on the project's final conference - Public - M36
D9.7 - ROXANNE's recommendations - Public - M36
D9.8 - Final report on the dissemination, exploitation - Public - M36
D9.9 - The project's communications plan update M18 - Public - M18
D9.10 - The project's communications plan update M36 - Public - M36
D9.11 - The project's dissemination and exploitation plan update M18 - Public - M18
D9.12 - The project's dissemination and exploitation plan update M36 - Public - M36
Final Conference Presentations
ROXANNE Final Conference - CRiTERIA project
ROXANNE Final Conference - CTC project
ROXANNE Final Conference - Ethics
ROXANNE Final Conference - Exploitation
ROXANNE Final Conference - INFINITY project
ROXANNE Final Conference - Introduction to Autocrime platform
ROXANNE Final Conference - Police use case1
ROXANNE Final Conference - Police use case2
ROXANNE Final Conference - Project achievements
ROXANNE Final Conference - Training platform
ROXANNE dissemination (status June 2023):
| S.No. | Date | Title | Status | Lead Partner | Conference/Journal |
| 1 | April 2020 | Idiap NMT System for WAT 2019Multi-Modal Translation Task | Published WAT Workshop, EMNLP2019 Hongkong | IDIAP | conference |
| 2 | April 2020 | Overview of the 6th Workshop on Asian Translation | Published WAT Workshop, EMNLP2019 Hongkong | IDIAP | conference |
| 3 | April 2020 | OdiEnCorp 2.0: Odia-English Parallel Corpus for Machine Translation | Published WILDRE Workshop LREC 2020 | IDIAP | conference |
| 4 | April 2020 | German News Article Classification: A Multichannel CNN Approach | ETAEERE 2020 conference, India, March 2020 | IDIAP | conference |
| 5 | April 2020 | Idiap Submissions to Swiss German Language Detection Shared Task | Published Swiss-German Language Detection Shared Task, SwissText and KONVENS 2020 | IDIAP | conference |
| 6 | April 2020 | Inferring Highly-dense Representations for Clustering Broadcast Media Content | Published Prague Bulletin of Mathematical Linguistic (PBML) Journal | IDIAP | journal |
| 7 | April 2020 | Incremental Semi-Supervised Learning for Multi-Genre Speech recognition | Accepted in ICASSP 2020 conference, Barcelona, May 2020 | IDIAP | conference |
| 8 | April 2020 | Distant Supervision and Noisy Label Learning for Low Resource Named Entity Recognition: A Study on Hausa and Yorùbá | Accepted by the workshop PML4DC under ICML 2020 | USAAR | conference |
| 9 | July 2020 | Idiap & UAM participation at GermEval 2020: Classification and Regression of Cognitive and Motivational Style from Text | Published GermEval 2020 Shared Task on the Classification and Regression of Cognitive and Motivational style from Text, SwissText and KONVENS 2020 | IDIAP | conference |
| 10 | July 2020 | Idiap and UAM Participation at MEX-A3T Evaluation Campaign | Published MEX-A3T@IberLEF2020 | IDIAP | conference |
| 11 | December 2020 | Robust link prediction in criminal networks: A case study of the Sicilian Mafia | Published | UCSC | journal |
| 12 | July 2020 | BertAA: Bert fine-tuning for Authorship Attribution | Accepted at ICON2020 | IDIAP | conference |
| 13 | July 2020 | Analysis of ABC Submission to NIST SRE 2019 CMN and VAST Challenge. | Proceedings of Odyssey 2020 The Speaker and Language Recognition Workshop, available in iSCA archive. | BUT | conference |
| 14 | July 2020 | Probabilistic embeddings for speaker diarization | Proceedings of Odyssey 2020 The Speaker and Language Recognition Workshop, available in iSCA archive. | BUT | conference |
| 15 | July 2020 | Utilizing VOiCES dataset for multichannel speaker verification with beamforming | Proceedings of Odyssey 2020 The Speaker and Language Recognition Workshop, available in iSCA archive. | BUT | conference |
| 16 | October 2020 | BUT text-dependent speaker verification system for SdSV 2020 challenge | Published in Interspeech 2020 | BUT | conference |
| 17 | June 2021 | Analysis of the BUT diarization system for VoxConverse challenge | Accepted for ICASSP 2021 | BUT | conference |
| 18 | June 2021 | Analysis of x-vectors for low resource speech recognition | Accepted for ICASSP 2021 | BUT | conference |
| 19 | September 2020 | Transfer Learning and Distant Supervisionfor Multilingual TransformerModels: A Study on African Languages | Got accepted by EMNLP2020. Curently preparing the camera-ready version. | USAAR | conference |
| 20 | October 2020 | Detection of Similar Languages and DialectsUsing Deep Supervised Autoencode | Published at ICON2020 | IDIAP | conference |
| 21 | October 2020 | ODIANLP’s Participation in WAT2020 | Published at WAT2020 (AACL workshop) | IDIAP | conference |
| 22 | December 2020 | On Node Embedding of Uncertain Networks | Published: IEEE BigDATA 2020 | LUH | conference |
| 23 | September 2021 | Graph2Speak: Improving Speaker Identification using Network Knowledge in Criminal Conversational Data | Accepted at SPSC Symposium | IDIAP | conference |
| 24 | July 2021 | Bayesian HMM clustering of x-vector sequences (VBx) in speaker diarization: theory, implementation and analysis on standard tasks | Published in Computer Speech and Language, Vol. 71 | PHO/BUT | journal |
| 25 | September 2021 | ROXSD: a Simulated Dataset of Communication in Organized Crime | Accepted at SPSC Symposium | All partners | conference |
| 26 | September 2021 | Open-Set Speaker Identification pipeline in live criminal investigations | Accepted at SPSC Symposium | IDIAP | conference |
| 27 | September 2021 | Multimodal Neural Machine Translation Systemfor English to Bengali | Accepted at First Workshop on Multimodal Machine Translation for Low Resource Languages (MMTLRL-2021), RANLP2021 | IDIAP | conference |
| 28 | October 2022 | Real-Time Multi-Vehicle Multi-Camera Tracking With Graph-Based Tracklet Features | Accepted at the TRB Annual Meeting 2022, Transportation Research Record | LUH | journal |
| 29 | October 2022 | Multivariate Time Series Analysis: An Interpretable CNN-based Model | Accepted at the 9th IEEE International Conference on Data Science and Advanced Analytics (DSAA 2022) | LUH | conference |
| 30 | October 2021 | On the Impact of Dataset Size: A Twitter Classification Case Study | Accepted at the 20th IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT 2021) | LUH | conference |
| 31 | October 2021 | BertOdia: BERT pre-training for low resource Odia language | Accepted at 2nd International Conference on Biologically Inspired Techniques in Many-Criteria Decision Making (BITMDM-2021) | IDIAP | conference |
| 32 | August 2022 | MANDO-GURU: Vulnerability Detection for Smart Contract Source Code By Heterogeneous Graph Embeddings | Accepted at the ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE 2022) | LUH | conference |
| 33 | August 2022 | MANDO: Multi-Level Heterogeneous Graph Embeddings for Fine-Grained Detection of Smart Contract Vulnerabilities | Accepted at the 9th IEEE International Conference on Data Science and Advanced Analytics (DSAA 2022) | LUH | conference |
| 34 | August 2022 | SoChainDB: A Database for Storing and Retrieving Blockchain-Powered Social Network Data | Accepted at 45th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2022) | LUH | conference |
| 35 | August 2022 | SparCAssist: A Model Risk Assessment Assistant Based on Sparse Generated Counterfactuals | Accepted at 45th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2022) | LUH | conference |
| 36 | August 2021 | Speaker embeddings by modeling channel-wise correlations | Published in Interspeech 2021 | BUT | conference |
| 37 | June 2022 | Analyzing Speaker Verification Embedding Extractors and Back-Ends Under Language and Channel Mismatch | Published in Odyssey | BUT | conference |
| 38 | June 2022 | Speaker Recognition on Mono-Channel Telephony Recordings | Published in Odyssey | BUT/MOPS-INP | conference |
| 39 | June 2022 | Development of ABC Systems for the 2021 Edition of NIST Speaker Recognition Evaluation | Published in Odyssey | BUT | conference |
| 40 | September 2022 | Training Speaker Embedding Extractors Using Multi-Speaker Audio with Unknown Speaker Boundaries | Published in Interspeech 2022 | BUT | conference |
| 41 | August 2021 | Speech Activity Detection Based on Multilingual Speech Recognition System | Published: ISCA Proc. Interspeech 2021 | IDIAP | conference |
| 42 | August 2021 | ROXANNE Research Platform: Automate criminal investigations and leverage multimodal fusion | Published: ISCA Proc. Interspeech 2021 | IDIAP | conference |
| 43 | May 2021 | NLPHut's Participation at WAT2021 | Published at WAT2021 (ACL-IJCNLP 2021 Workshop) | IDIAP | conference |
| 44 | 2021 | BUT System Description for The Third DIHARD Speech Diarization Challenge | Proceedings available at Dihard Challenge Github | BUT | conference |
| 45 | Mar.21 | Analysing the Noise Model Error for Realistic Noisy Label Data | AAAI-2021 | USAAR | conference |
| 46 | 2022 | Is BERT Robust to Label Noise? A Study on Learning with Noisy Labels in Text Classification | ACL-2022 Insight Workshop | USAAR | conference |
| 47 | 2022 | Task-Adaptive Pre-Training for Boosting Learning With Noisy Labels: A Study on Text Classification for African Languages | ICLR2022 AfricaNLP Workshop | USAAR | conference |
| 48 | Apr.21 | Open Machine Translation for Low Resource South American Languages(AmericasNLP 2021 Shared Task Contribution) | Published at AmericasNLP (NAACL-HLT 2021 workshop) | IDIAP | conference |
| 49 | 2021 | Estimating Formulas for Model Performance Under Noisy Labels Using Symbolic Regression | ESANN 2021 | USAAR | conference |
| 50 | 2022 | TOKEN is a MASK: Few-shot Named Entity Recognition with Pre-trained Language Models | 25th International Conference on Text, Speech and Dialogue (TSD 2022) | USAAR | conference |
| 51 | 2022 | A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation | NAACL-2022 | USAAR | conference |
| 52 | May 2023 | Meta Self-Refinement for Robust Learning with Weak Supervision | EACL 2023 | USAAR | conference |
| 53 | May 2023 | Weaker Than You Think: A Critical Look at Weakly Supervised Learning | ACL 2023 | USAAR | conference |
| 54 | 2023 | Multi-Vehicle Multi-Camera Tracking with Graph-Based Tracklet Features | IEEE Transactions on Multimedia journal | LUH | journal |
| 55 | 2023 | Inductive and Transductive Link Prediction for Criminal Network Analysis | Journal of Computational Science | LUH, UCSC, MOPS-INP | journal |
| 56 | 2024 | Implementing contextual biasing in GPU decoder for online ASR (accepted for publication) | INTERSPEECH 2023 | IDIAP | conference |
| 57 | 2024 | CommonAccent: Exploring Large Acoustic Pretrained Models for Accent Classification Based on Common Voice (accepted for publication) | INTERSPEECH 2023 | IDIAP | conference |
| 58 | 2020 | Supervised domain adaptation for text-independent speaker verification using limited data (published) | INTERSPEECH 2020 | IDIAP | conference |
| 59 | 2021 | Multi-task Neural Network for Robust Multiple Speaker Embedding Extraction (published) | INTERSPEECH 2021 | IDIAP | conference |
| 60 | 2022 | Team Innovators at SemEval-2022 for Task 8: Multi-Task Training with Hyperpartisan and Semantic Relation for Multi-Lingual News Article Similarity (published) | Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), NAACL 2022 | IDIAP | conference |
| 61 | 2022 | Innovators@SMM4H'22: An Ensembles Approach for self-reporting of COVID-19 Vaccination Status Tweets (published) | International Conference on Computational Linguistics (COLING 2022) | IDIAP | conference |
| 62 | 2022 | IDIAP_TIET@LT-EDI-ACL2022 : Hope Speech Detection in Social Media using Contextualized BERT with Attention Mechanism (published) | ACL | IDIAP | conference |
| 63 | 2022 | IDIAP Submission@LT-EDI-ACL2022: Homophobia/Transphobia Detection in social media comments (published) | ACL 2022 | IDIAP | conference |
| 64 | 2022 | IDIAP Submission@LT-EDI-ACL2022: Detecting Signs of Depression from Social Media Text (published) | ACL 2022 | IDIAP | conference |
| 65 | 2022 | IDIAP Submission@LT-EDI-ACL2022 : Hope Speech Detection for Equality, Diversity and Inclusion (published) | ACL 2022 | IDIAP | conference |
| 66 | 2022 | HMIST: Hierarchical Multilingual Isometric Speech Translation using Multi-Task Learning Framework for Automatic Dubbing (published) | PACIFIC ASIA CONFERENCE ON LANGUAGE, INFORMATION AND COMPUTATION (PACLIC 2022), In Proceedings of ACL Anthology | IDIAP | conference |
| 67 | 2022 | Hierarchical Multi-task learning framework for Isometric-Speech Language Translation (published) | ACL 2022 | IDIAP | conference |
| 68 | 2022 | DeepCon: An End-to-End Multilingual Toolkit for Automatic Minuting of Multi-Party Dialogues (published) | Special Interest Group on Discourse and Dialogue (SIGDIAL 2022) | IDIAP | conference |
| 69 | 2022 | Bio-Medical Multi-label Scientific Literature Classification using LWAN and Dual-attention module (published) | PACIFIC ASIA CONFERENCE ON LANGUAGE, INFORMATION AND COMPUTATION (PACLIC 2022), In Proceedings of ACL Anthology | IDIAP | conference |
| 70 | 2022 | Automatic Summarization for Creative Writing: Denoising Auto-Encoder based Pipeline Method for Generating Summary of Movie Scripts (published) | International Conference on Computational Linguistics (COLING 2022) | IDIAP | conference |
| 71 | 2022 | An End-to-End Multilingual System for Automatic Minuting of Multi-Party Dialogues (published) | Pacific Asia Conference on Language, Information and Computation (PACLIC 36), In proceedings of ACL Anthology | IDIAP | conference |
| 72 | 2022 | An Empirical Comparison of Semantic Similarity Methods for Analyzing down-streaming Automatic Minuting task (published) | Pacific Asia Conference on Language, Information and Computation (PACLIC 36), In proceedings of ACL Anthology | IDIAP | conference |
| 73 | May 2023 | Frequent-words analysis for forensic speaker comparison | Speech communication journal | NFI | journal |
|
In preparation
|
|||||
| 74 | 2023 | Speaker recognition on mono-channel telephony recordings (This paper will be a journal extension of the conference paper with the same title listed in the above table) |
Under discussion | (BUT, MOPS-INP) | not decided |
| 75 | 2023 | ROXANNE investigative platform (publication planned as collective dissemination in a journal of forensics science, plan for submission is June 2023) |
Under discussions (planned submission time – end June 2023) Update on paper (see 42 in D9.8) |
IDIAP, all | journal |
| 76 | 2023 | ROXSD data (ROXSD publication in Forensic Science International: Digital Investigation, plan for submission is June 2023) |
Journal of Forensic Science International ((planned submission time – end June 2023) Update on the paper (see 25 in D9.8) |
HENS, all | journal |
| 77 | 2023 | Entity Matching Across Small Networks Using Node Attributes (under review in CIKM 2023 - Conference on Information and Knowledge Management) |
CIKM 2023 | LUH, IDIAP, LUH, PHO, HENS | conference |
Prepared submissions (require a request access)