Logiciels
L'Institut a à son compte de nombreux logiciels largement utilisés et a une longue tradition de diffusion des résultats de la recherche par le biais de licences libres et de mise à disposition des travaux. Cet engagement va au-delà des simples contributions logicielles. L'Idiap participe activement à de nombreux projets, qu'il s'agisse d'initiatives à petite échelle ou de projets de grande envergure. Pour faciliter le partage des améliorations apportées par ses chercheurs avec la communauté au sens large, l'institut a conclu divers accords de licence de contributeur d'entreprise (CLA) ou des accords équivalents avec la Qt Company, le Python Project, la Cloud Native Computing Foundation, la Cloud Foundry Foundation et Google. Grâce à ces CLA, les employés de l'Idiap peuvent contribuer à des projets open-source de grande envergure.
L'Idiap crée et met à disposition un nombre important de logiciels professionnels. Au cours des cinq dernières années, l'Institut a communiqué à propos de 206 logiciels, ce qui a permis la distribution de 122 logiciels open source et l'octroi de 84 licences commerciales sur des brevets et des logiciels.
Fast Transformers, PyDHN, Kaldi et Bob sont des exemples de logiciels créés par l'Idiap. Le projet Github Fast Transformers, qui compte plus de 1400 étoiles et plus de 160 forks, a été utilisé dans Muzic, un projet de Microsoft pour la compréhension et la génération de musique. Le logiciel libre PyDHN, destiné à la simulation physique des réseaux de chauffage urbains, calcule la pression, la température et le débit massique à l'intérieur de la tuyauterie sans connaitre les conditions aux limites au niveau des centrales et des sous-stations. Ce logiciel est inclus dans des outils SIG libres pour un impact plus large sur la société. L'outil libre Kaldi pour la modélisation de la parole, considéré comme l'une des principales technologies de la communauté recherche et l'innovation, a reçu 6781 citations. Bob, un ensemble d'outils open-source visant à promouvoir la recherche reproductible, compte 25 versions, plus de 100 dépôts satellites et plus de 5'000 commits sur le dépôt central.
L'Idiap contribue à la communauté scientifique grâce aux logiciels libres listés ci-dessous. Si vous avez des questions sur un logiciel spécifique, veuillez utiliser ce formulaire de contact.
| NOM DU LOGICIEL | DESCRIPTION (en anglais uniquement) |
|---|---|
| aberration_correction | Sorting and scanning aberration correction of periodic image time-series. |
| abroad-re | Relation Extraction in underexplored biomedical domains: A diversity-optimised sampling and synthetic data generation approach |
| acoustic-simulator | Implementation of audio degradation processes. |
| act | ACT for Accuracy of Connective Translation is a reference-based metric to measure the accuracy of discourse connective translation, mainly for statistical machine translation systems. |
| als-classification | Classification of ALS and Stress in Cultures of Motor Neurons. |
| analogy_learning | Can language models learn analogical reasoning? Investigating training objectives and comparisons to human performance |
| Anonymization | Text anonymization is a Python library for anonymizing sensitive information in text data. Focused on Swiss French banking data. |
| APT | The APT software is a reference-based metric to evaluate the accuracy of pronoun translation. |
| asrt | A python library that facilitate the extraction of text sentences from multilingual 'pdf' documents |
| atco2-corpus | A Large-Scale Dataset for Research on Automatic Speech Recognition and Natural Language Understanding of Air Traffic Control Communications |
| Attentive_Residual_Connections_NMT | Implementation and output data of "Global-Context Neural Machine Translation through Target-Side Attentive Residual Connections" |
| attention-sampling | Python library to accelerate the training and inference of neural networks on large data. This code is the reference implementation of the methods described in our ICML 2019 publication "Processing Megapixel Images with Deep Attention-Sampling Models". |
| bayesian-peft | Bayesian Parameter-Efficient Fine-Tuning for Overcoming Catastrophic Forgetting |
| bayesian-recurrence | A Bayesian Interpretation of Recurrence in Neural Networks |
| beat.accumos.exporter | This module implements a tool that will generate Acumos compatible Docker images from simple BEAT algorithms (sequential, without setup nor prepare). |
| BEAT platform | The BEAT platform is a European computing e-infrastructure for Open Science proposing a solution for open access, scientific information sharing and re-use including data and source code while protecting privacy and confidentiality. It allows easy online access to experimentation and testing in computational science. |
| benefits-of-max-pooling | This folder contains the supplementary material for the paper 'Benefits of Max Pooling in Neural Networks: Theoretical and Experimental Evidence' TMLR 2023 |
| bert-text-diarization-atc | BERTraffic: BERT-based Joint Speaker Role and Speaker Change Detection for Air Traffic Control Communications |
| bioformats_io | Takes as input NPY files and saves them to OME or OME-TIFF, and conversely, takes as input microscopy-format files and saves them as NPY. |
| BOB | Bob is a free signal-processing and machine learning toolbox developed by the Biometrics group at Idiap Research Institute, Switzerland. The toolbox is written in a mix of Python and C++ and is designed to be both efficient and reduce development time. |
| bob.bio.spear | Implements speaker recognition algorithms. |
| bob.bio.vein | Vein biometrics recognition baselines. |
| bob.ip.binseg | Binary Segmentation Benchmark Package for Bob. |
| bob.ip.qualitymeasure | This package is part of the signal-processing and machine learning toolbox Bob. It provides functions for extracting image-quality features proposed for PAD experiments by different research groups. Image quality measures proposed by Galbally et al. (IEEE TIP 2014) and by Wen et al. (IEEE TIFS 2015) are implemented in this package. |
|
Active Tuberculosis Detection On CXR Package for Bob |
|
| bob.paper.deep_pix_bis_pad.icb2019 |
This package is part of the signal-processing and machine learning toolbox Bob. Deep Pixel-wise Binary Supervision for Face Presentation Attack Detection |
| bob.paper.deft_ijcb2024 | Demographic Fairness Transformer for Bias Mitigation in Face Recognition |
| bob.paper.eusipco2018 | Speaker Inconsistency Detection in Tampered Video. Source code for reproducing the speaker inconsistency detection experiments of the paper "Speaker Inconsistency Detection in Tampered Video" in EUSIPCO 2018 conference. |
| bob.paper.fg2024_breaking_btp | Breaking Template Protection: Reconstruction of Face Images from Protected Facial Templates |
| bob.paper.icassp2020_domain_guided_pruning | Code to reproduce "Domain Adaptation for Generalization of Face presentation Attack Detection in Mobile Settings with Minimal Information" ICASSP 2020 paper. |
| bob.paper.icassp2020_facepad_generalization_infovae | Code to reproduce "Improving Cross-dataset Performance Of Face Presentation Attack Detection Systems Using Face Recognition Datasets" ICASSP 2020 paper. |
| bob.paper.icassp2022_morph_generate | Source code for generating the morphs described in the ICASSP 2022 paper 'Are GAN-based Morphs Threatening Face Recognition?'. |
| bob.paper.icassp2024_diu_hfr | Heterogeneous Face Recognition Using Domain Invariant Units |
| bob.paper.icassp2024_face_ti_partial | Face Reconstruction from Partially Leaked Facial Embeddings |
| bob.paper.iccv2023_face_ti | Template Inversion Attack against Face Recognition Systems using 3D Face Reconstruction |
| bob.paper.icip2022_face_reconstruction | Face Reconstruction from Deep Facial Embeddings using a Convolutional Neural Network |
| bob.paper.icip2023_blackbox_face_reconstruction | Blackbox Face Reconstruction from Deep Facial Embeddings Using A Different Face Recognition Model (ICIP 2023) |
| bob.paper.ijcb2023_caim_hfr | Bridging the Gap: Heterogeneous Face Recognition with Conditional Adaptive Instance Modulation |
| bob.paper.ijcb2023_vuln_analysis_hyg_mask_attack | This package is part of the signal-processing and machine learning toolbox Bob. |
| bob.paper.ijcb2023_face_ti | Inversion of Deep Facial Templates using Synthetic Data |
| bob.paper.ijcb2024_agnostic_features_mad | Morphing attack detection using attack-agnostic features |
| bob.paper.tbiom2024_face_ti | Template Inversion Attack Using Synthetic Face Images Against Real Face Recognition Systems |
| bob.paper.ijcb2024_moe_hfr | Modality Agnostic Heterogeneous Face Recognition with Switch Style Modulators |
| bob.paper.makeup_aim | This package contains python code to reproduce experiments and results described in the IEEE T-BIOM paper: "Detection of Age-Induced Makeup Attacks on Face Recognition Systems Using Multi-Layer Deep Features" |
| bob.paper.mcae.icb2019 | Face PAD using multi-channel autoencoders. |
| bob.paper.mccnn.tifs2018 | Face PAD using Multi-Channel CNN. |
| bob.paper.neurips2023_face_ti | Face Reconstruction from Facial Templates by Learning Latent Space of a Generator Network |
| bob.paper.nir_patch_pooling | This package contains python code to reproduce experiments and results described in the IEEE ICIP paper: "CNN Patch Pooling for Detecting 3D Mask Presentation Attacks in NIR". |
| bob.paper.sensl2023_hires_codedaper | Toward High-Resolution Face Image Generation From Coded Aperture Camera |
| bob.paper.tbiom2021_protect_vascular_dnn_biohash | Code to reproduce the results for the paper "Towards Protecting and Enhancing Vascular Biometric Recognition methods via Biohashing and Deep Neural Networks" in IEEE-TBIOM. |
| bob.paper.tifs2024_face_ti | Vulnerability of State-of-the-Art Face Recognition Models to Template Inversion Attack |
| bob.paper.tifs2024_model_pairing | Model Pairing Using Embedding Translation for Backdoor Attack Detection on Open-Set Classification Tasks |
| bob.paper.tpami2023_face_TI | Comprehensive Vulnerability Evaluation of Face Recognition Systems to Template Inversion Attacks via 3D Face Reconstruction |
| bob.paper.vrbiom_pad_ijcb2024 | Assessing the Reliability of Biometric Authentication on Virtual Reality Devices |
| bob.paper.wacv2024_dvpba | Mitigating Demographic Bias in Face Recognition via Regularized Score Calibration |
| bob.paper.wifs2021_biohashing_sota_face | On the Recognition Performance of BioHashing on state-of-the-art Face Recognition models |
| bob.paper.xcsmad_facepad | Face PAD for Silicone mask-based attack detection. |
| bob.rppg.base | This package provides three baseline algorithms to perform remote photoplethysmography (rPPG), which consists in measuring the heart rate from a face video sequence. The software package implements three different algorithms to retrieve the pulse signal from skin color variations: an approach based on colorspace transformation, another approach solely based on signal processing, and a more recent approach, which analyzes the subspace spanned by skin-colored pixels in the RGB colorspace. |
| buslr | Build System for Speech and Language Research. |
| CBI-MMTools | This repository contains plugins, device adapters and libraries for the operation of microscopy platforms using Micro-Manager, developed by the Computational BioImaging group at Idiap Research Institute. |
| cbi_toolbox | CBI Toolbox is a collection of algorithms used for computational bioimaging and microscopy. |
| ccdbhg-head-gesture-recognition | CCDbHG Head Gesture Dataset |
| cncsharedtask | IDIAPERS @ CASE22-TASK 3: Event Causality Identification |
| CNN-based Models | CNN-based Models for ALS and stressed MNs cultures classification. |
| CNN_QbE_STD | Implementation of the work presented in "CNN based Query by Example Spoken Term Detection". |
| CNN-voice-PAD | The purpose of this software is to train Convolutional Neural Networks on raw speech signals in order to detect voice presentation attacks. |
| cbrec | Content-Based Recommendation Generator (CBRec v1.0). A Python library which generates content-based recommendations for a set of items described by textual metadata using four possible vector space methods, namely TF-IDF, LSI, RP and LDA. |
| code.face_rec_lensless | Face Recognition Using Lensless Camera (ICASSP 2024) |
| code.group_membership_verification | Group Membership Verification via Nonlinear Sparsifying Transform Learning |
| contextual-biasing-on-gpus | The implementation of the contextual biasing for ASR decoding on GPUs without lattice generation |
| symfony-bundle-datacryptographer | The Data Cryptographer Bundle is a PHP/Symfony bundle which provides a cryptographer resource/service for common cryptographic operations. |
| deepdefresneling | Deep Learning Methods for Digital Holography in an Embedded System |
| DeepFocus | Code for the PyTorch implementation of "DeepFocus: a Few-Shot Microscope Slide Auto-Focus using a Sample Invariant CNN-based Sharpness Function". |
| DeepOBS |
A Deep Learning Optimizer Benchmark Suite. |
| depth_human_synthesis | DepthHuman: A tool for depth image synthesis for human pose estimation |
| DepthInSpace | [ICCV 2021] DepthInSpace: Exploitation and Fusion of Multiple Frames of a Video for Structured-Light Depth Estimation |
| DHgeN | is a Python module for generating District Heating Networks layouts. |
| dialog2flow | Dialog2Flow: Convert Your Dialogs to Flows! |
| DiscoConn-Classifier | Classifier models and feature extractors for discourse relations. |
| distance-based-cnn | Automatic Dysarthric Speech Detection Exploiting Pairwise Distance-based Convolutional Neural Networks |
| DRILL | Deep residual output layers for neural language generation. |
| DocRec | KEYWORD EXTRACTION AND DOCUMENT RECOMMENDATION IN CONVERSATIONS (DocRec). The package contains several pieces of Matlab code. Taken together, they extract keywords from a conversation, then use them to build implicit queries, and then consolidate the sets of retrieved documents to recommend to the conversation participants. |
| eakmeans | Implementation of fast exact k-means algorithms. |
| Eigenposterior | Eigenposterior (Senone Class Principal Components) based approach for purifying DNN posterior estimates. |
| emorec | Emotion-Based Recommendation Generator (EMORec v1.0). A Python library which performs emotion-based analysis and recommendation using a multiple-instance regression algorithm for a set of multimedia items described by transcripts. |
| ergodic_sketching_ros | This repository contains the source code to run the drozBot portraitist robot over ROS1. It contains 3 different packages: ergodic_sketching; ergodic_sketching_msgs; ergodic_sketching_ros; ilqr_planner. |
| ESLAM | Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields |
| Exact Acceleration of Linear Object Detectors | We describe a general and exact method to considerably speed up linear object detection systems operating in a sliding, multi-scale window fashion, such as the individual part detectors of part-based models. |
| ExVo-2022 | Extracting pre-trained self-supervised embeddings for ICML ExVO 2022 challenge |
| facecolormodel | This page contains the source code and data needed to train and use a model for skin, hair, clothing and background color modelling and segmentation. |
| facereclib | This library is designed to perform a fair comparison of face recognition algorithms. It contains scripts to execute various kinds of face recognition experiments on a variety of facial image databases. |
| Factual-Reporting-and-Political-Bias-Web-Interactions | Mapping the Media Landscape: Predicting Factual Reporting and Political Bias Through Web Interactions |
| fast_pose_machines | Efficient Pose Machines for Multi-Person Pose Estimation. |
| FiniteStateTransducers.jl | Play with Weighted Finite State Transducers (WFSTs) using the Julia language. |
| flowestimation | Code for the PyTorch implementation of "Estimating Nonplanar Flow from 2D Motion-blurred Widefield Microscopy Images via Deep Learning", submitted to IEEE ISBI, 2021 |
| fluoMNs_models | CNN-based Models for ALS and stressed MNs cultures classification. |
| fullgrad-saliency | This code is the reference implementation of the methods described in our NeurIPS 2019 publication "Full-Gradient Representation for Neural Network Visualization. This repository implements two methods: the reference FullGrad algorithm, and a variant called "simple FullGrad", which omits computation of bias parameters for bias-gradients. |
| gafar | GaFaR: Geometry-aware Face Reconstruction |
| gafro | Geometric Algebra For RObotics |
| gafro_benchmarks | This repository contains benchmarks for the gafro library compared to other robot kinematics and dynamics libraries. |
| gafro_robot_descriptions | This repository contains classes of different robot descriptions for the usage with the gafro library. |
| gafro_ros | ROS visualization and URDF conversion for the gafro library |
| gafro_examples | This repository contains some examples on how to use the gafro library |
| GC.MI | The gc_MI.cpp file includes C++ code implementing the GC.MI algorithm. |
| GeoNeRF | Generalizing NeRF with Geometry Priors |
| gme-sampler | Greedy Maximum Entropy Sampler |
| HAN_NMT | Document-Level Neural Machine Translation with Hierarchical Attention Networks. |
| HEAT Image Retrieval System | HEAT is an image retrieval web-application that is intended for large unstructured collections of images without semantic annotations. The system implements a novel searching paradigm that does not require any explicit query. At each iteration, the system displays a small set of images and the user chooses the image that best matches what she is looking for. After a few iterations, the sets of displayed images are gradually concentrated on images that satisfy the user. |
| Temporal Super-Resolution Microscopy Using a Hue-Encoded Shutter. | |
| g3e | HG3D - A module for 3D head pose and gaze tracking from RGB-D sensors. This software contains the implementation of algorithms related to 3D head pose and gaze tracking tasks based on RGB-D cameras (standard vision and depth). |
| hallucination-detection | This repository contains the code and data for the paper Unsupervised Token-level Hallucination Detection from Summary Generation By-products by Andreas Marfurt and James Henderson, presented at the GEM workshop at EMNLP 2022. |
| hourglass_push | This repository contains Python code for the work presented in the IROS 2021 paper "An Efficient Image-to-Image Translation HourGlass-based Architecture for Object Pushing Policy Learning" by M. Ewerton, A. Martínez-González and JM. Odobez. |
| HOOSC | Histogram of Orientation Shape Context. |
| HPCA | hpca is a C++ toolkit providing an efficient implementation of the Hellinger PCA for computing word embeddings. |
| human-detection | Background substraction and Human Detection. |
| HTS-VTLN | This software is a patch to HMM based statistical parametric speech synthesis toolkit (HTS 2.2). |
| HyperMixing | HyperMixing is a token-mixing techniques to be used as linear-time alternative to attention, for example in Transformer-like architecture like HyperMixer. |
| icassp2024.dvpf | Deep Variational Privacy Funnel: General Modeling with Applications in Face Recognition |
| icassp-oov-recognition | This has data and code related to the paper accepted at ICASSP21 "A comparison of methods for OOV-word recognition on a new Public Dataset". |
| identifying-privacy-personas | Identifying Privacy Personas |
| idiap_spe | Set of exercises on automatic speech processing. |
| IdiapTTS | Idiap Text-to-Speech system developed at the Idiap Research Institute. |
| ihper | (Idiap human perception system). An audio-visual system for human perception, human-robot interaction. This ROS-compatible system detects tracks faces, re-identifies people, detect speaking people, and non-verbal cues (nod, visual focus of attention). |
| importance-sampling | This python package provides a library that accelerates the training of arbitrary neural networks created with Keras using importance sampling. |
| inference-from-real-world-sparse-measurements | Inference from Real-World Sparse Measurements - MALAT |
| inv-tn | Inverse Text Normalization using NMT models. |
| ISS | The Idiap Speech Scripts (ISS) is a collection of speech databases and dictionaries, and for training and testing of models for ASR. The scripts in turn are reliant on many other packages including HTK/HTS, Juicer and the ICSI speech tools. |
| itm | Image-guided topic modeling for interpretable privacy classification |
| joint-embedding-nmt | Pytorch implementation of the structure-aware output layer for neural machine translation which was presented at WMT 2018. |
| kaldi-ivector | The code is an implementation of the standard i-vector extraction algorithm for the Kaldi toolkit. |
| KiSC | K.I.S.S. Cluster (KiSC) - with K.I.S.S. as in "Keep It Stupid Simple" - is a utility that aims to simplify the life of administrators managing resources accross a cluster of hosts. |
| libssp | Library for speech signal processing. |
| fast-transformers | This library aims to facilitate research on efficient transformer models and provides PyTorch implementations for several efficient transformers. |
| language-label-bias | This repository contains the code for our paper "Understanding the effects of language-specific class-imbalance in multilingual fine-tuning". |
| LR-CNN | Trains low-rank CNNs from raw speech using Keras/Tensorflow, with inputs from Kaldi directories. |
| mash | Back-end of the MASH computation farm. |
| mash-simulator | mash-simulator is a 3D simulator for Linux and MacOS where a robot must complete a certain number of tasks in different randomized environments. |
| mash-web | Front-end of the MASH computation farm. |
| ML3 | ML3 is an open source implementation of the Multiclass Latent Locally Linear Support Vector Machine algorithm, a multi-class local classifier based on a latent SVM formulation. |
| mhan | Multilingual hierarchical attention networks toolkit. |
| model-uncertainty-for-adaptation | Code for paper Uncertainty Reduction for Model Adaptation in Semantic Segmentation at CVPR 2021 |
| morphgen | Face morphing attack generation |
| MSER | Linear time Maximally Stable Extremal Regions (MSER) implementation as described in D. Nistér and H. Stewénius, Linear Time Maximally Stable Extremal Regions". |
| multicamera-calibration | This toolset provides the basics for calibrating a multi-camera scene. it contains six utilities for different purposes. In this README I will walk the user through the calibration of a multi camera scene using this toolset. |
| multimodal_gaze_target_prediction | This repo provides the training and testing code for our paper "A Modular Multimodal Architecture for Gaze Target Prediction: Application to Privacy-Sensitive Settings" published at the GAZE workshop at CVPR 2022. |
| nnsslm | Neural Network based Sound Source Localization Models. |
| News-Media-Reliability | Reliability Estimation of News Media Sources: "Birds of a Feather Flock Together" |
| Node_weighted_GCN_for_depression_detection | Node-weighted Graph Convolutional Network for Depression Detection in Transcribed Clinical Interviews |
| NVIB | Nonparametric Variational Information Bottleneck |
| nvib_transformers | A VAE for transformers using Nonparametric Information bottleneck |
| pbdlib-matlab | PbDlib is a set of tools combining statistical learning, dynamical systems and optimal control approaches for programming-by-demonstration applications. |
| pddetection-reps-learning | Supervised Speech Representation Learning for Parkinson's Disease Classification |
| phonvoc | Phonetic and phonological vocoding platform. Phonvoc is a cascaded deep neural network composed of speech analyser and synthesizer that use shared phonological speech representation. |
| pkwrap |
This is a (yet another!) python wrapper for Kaldi. The main goal is to be able to train acoustic models in Pytorch so that we can
|
| policy-interpretations | This repository contains the code and links to the data and trained models for the paper Generating Interpretations of Policy Announcements presented at the NLP4DH workshop at EMNLP 2024. |
| potr | Pose Transformers: Human Motion Prediction with Non-Autoregressive Transformers |
| ppsdf |
Piecewise polynomial SDF(ppSDF) Supplementary code examples for Online learning of Continuous Signed Distance Fields Using Piecewise Polynomials. Contains code demos of continuous learning of a basis-function SDF representation from point cloud data, sampled from mesh files. Also contains a script for downloading the YCB dataset examples. Based on the paper: |
| probamod-v1 | Probabilistic Models: temporal topic models and more. Topic models such as Latent Dirichlet Allocation (LDA) have been used successfully in many domains for data mining. Originally designed for text documents, these methods find some hidden “topics” considering that each document is a weighted mixture of topics. Each topic expresses itself in a document by generating some specific words with more probability than others. |
| psfestimation | Code for the PyTorch implementation of "Spatially-Variant CNN-based Point Spread Function Estimation for Blind Deconvolution and Depth Estimation in Optical Microscopy", IEEE Transactions on Image Processing, 2020. |
| pydhn | PyDHN is a Python library for storing, visualizing and managing District Heating Network (DHN) data, running simulations and automate I/O workflow, built on top of Networkx. |
| pygafro | Geometric Algebra For RObotics in Python |
| RawSpeechClassification | Trains CNN (or any neural network based) classifiers from raw speech using Keras and tests them. The inputs are lists of wav files, where each file is labelled. It then creates fixed length signals and processes them. During testing, it computes scores at the utterance or speaker levels by averaging the corresponding frame-level scores from the fixed length signals. |
| RDF | Code for paper "Learning Robot Geometry as Distance Fields: Applications to Whole-body Manipulation" |
| rethinking-saliency | Saliency Map Interpretability as Generative Modelling |
| Residual_pose | Residual Pose: A Decoupled Approach for Depth-based 3D Human Pose Estimation. |
| rgbd | RGBD: A Python based RGB-D data processing module. This python module implements the streaming, calibration and visualization of RGB-D data, that is, combined color and depth images. |
| robust_pl | Robust Manipulation Primitive Learning via Domain Contraction (CoRL 2024) |
| sae_lang_detect | sae_lang_detect: Supervised Autoencoder for Language Detection. The Supervised Autoencoder (SAE) with Bayesian Optimization (BO) for the language detection task found effectively for discriminating between very close languages or dialects. This library contains the PyTorch implementation of SAE with one sample code for using it for the language detection task. The library can be used for other NLP classification tasks (e.g. Fake News Detection, Operant Motive Detection) easily. It supports both CPU and GPU versions with just turn on/off the GPU flag ("is_gpu = True or False"). |
| semiblindpsfdeconv | Semi-blind Spatially-Variant Deconvolution. Code for "Semi-Blind Spatially-Variant Deconvolution in Optical Microscopy with Local Point Spread Function Estimation By Use Of Convolutional Neural Networks" ICIP 2018. |
| sentence-planner | This is the code for the paper Sentence-level Planning for Especially Abstractive Summarization presented at the New Frontiers in Summarization workshop at EMNLP 2021. |
| sg_latent_modeling | StyleGAN3 Latent Space Modeling |
| sharingan | A Transformer Architecture for Multi-Person Gaze Following |
| sigma-gpt | σ-GPT: A New Approach to Autoregressive Models |
| simple-imager | Simple Imager (Linux Imaging and Deployment Made Easy) is a set of tools allowing an imaging server to retrieve a copy of Linux reference hosts (sources) and allowing those images to be deployed to other target hosts by the mean of RSync or BitTorrent files download. |
| sleepless | Benchmarks for sleep phase detection from polysomnographs |
| slog | Similarity Learning on Graph. SLOG contains implementation of similarity learning methods over relational data, where the relation between data points are given explicitly. |
| slu_representations | Effectiveness of text, acoustic, and lattice-based representations in spoken language understanding tasks |
| SpArch | Spiking Architectures for Speech Technology |
| sparse | SPARSE: Spiking Architectures towards Realistic Speech Encoding |
| IBDiarization | Speaker Diarization Toolkit. The toolkit is intended to facilitate research in multistream speaker diarization providing a platform for research in novel audio, video or location features. It is based on the Information Bottleneck principle and is explicitely designed to use of several hetergenous feature streams. |
| ssl-caller-detection | Can Self-Supervised Neural Representations Pre-Trained on Human Speech distinguish Animal Callers? |
| SSP | SSP stands for Speech Signal Processing. It is a fairly small package written in python. Its functionality is similar to tracter, with some overlap and some additional capabilities. In particular, SSP contains a parametric vocoder, a pitch extractor and feature extraction for ASR. |
| symfony-bundle-datajukebox | The Data Jukebox Bundle is a PHP/Symfony bundle which aims to provide - for common CRUD (Create-Read-Update-Delete) operations - the same level of abstraction that Symfony does for forms. |
| TactileErgodicExploration | A Python package for ergodic control on point cloud using diffusion. It is supplementary material for the paper "Tactile Ergodic Control Using Diffusion and Geometric Algebra." The package uses Laplacian eigenbasis for computing the potential field resulting from the diffusion on the point cloud. Then, it uses the heat-equation-driven area coverage (HEDAC) method to guide the exploration agents for tactile ergodic control tasks. This research is conducted at the Robot Learning and Interaction group of the Idiap Research Institute. |
| Tasting Families of Features for Image Classification | Please find below the code necessary to reproduce the experiments of the paper Tasting Families of Features for Image Classification "under the GPL v2 license." |
| tf_robot_learning | Tensorflow robot learning library. |
| The Multi-Tracked Paths | This is an implementation of the variant of KSP for tracking presented in (Berclaz et al. 2011). You can get more information and the reference implementation from the CVLab's web page about multi-camera tracking. |
| TIDIGITSRecipe.jl | This repository contains a recipe for training an automatic speech recognition (ASR) system using the TIDIGITS database. |
| tnn | TNN - Trajectory Nearest Neighbors. This code was developed as a part of the Innosuisse MALAT: Machine Learning for Air Traffic project, which is a partnership between SkySoft ATM and the Idiap Research Institute. |
| Torch | Statistical machine learning library containing most of the state-of-the-art algorithms. Written in Lua and C, the library is distributed under a BSD license. |
| torgo_asr | This is a Kaldi recipe to build automatic speech recognition systems on the Torgo corpus of dysarthric speech. |
| translation-aided-slu | This it the reference code for the paper The Interpreter Understands Your Meaning: End-to-end Spoken Language Understanding Aided by Speech Translation. |
| trimed | The trimed algorithm for obtaining the medoid of a set. |
| t-softmax | t-softmax pytorch reproducibility code. The repository contains the code to reproduce the results of the paper: Niccolò Antonello, Philip N. Garner "A t-distribution based operator for enhancing out of distribution robustness of neural network classifiers," IEEE Signal Processing Letters, 2020, to appear. |
| ttgo | TTGO:Tensor Train for Global Optimization Problems in Robotics. A PyTorch implementation of TTGO algorithm and the applications presented in the paper "Tensor Train for Global Optimization Problems in Robotics " |
| unet.interspeech2019 | U-NET based feature extractor for text-independent speaker verification. |
| unsupervised_gaze_calibration | This code allows the robust and unsupervised calibration of a gaze estimator used in a conversation or an object manipulation setting. It relies on task-related contextual attention prior to gather calibration samples and on robust estimation to compute the calibration parameters. |
| w2v2-air-traffic | How Does Pre-trained Wav2Vec 2.0 Perform on Domain Shifted ASR? An Extensive Benchmark on Air Traffic Control Communications |
| vilora | A Bayesian Interpretation of Adaptive Low-Rank Adaptation |
| warca | WARCA is a simple and fast algorithm for metric learning. |
| wav2vec-lfmmi | wav2vec-lfmmi provides recipes from fine-tuning a pre-trained wav2vec 2.0 model using the espresso tool kit. |
| Webvalidation | This software is a multi users, multi projects web annotation tool that help to organize the process of validating automatically generated transcriptions. |
| wmil-sgd | A weighted multiple-instance learning algorithm based on stochastic gradient descent. |
| xbob.thesis.elshafey2014 | This package contains scripts to reproduce the experiments of Laurent El Shafey's Ph.D. thesis at Ecole Polytechnique Fédérale de Lausanne (EPFL). |
| zentas | Software for doing k-medoids using an accelerated CLARANS algorithm. |
| zff_vad | Unsupervised Voice Activity Detection by Modeling Source and System Information using Zero Frequency Filtering |
Obsoleted Software
| Juicer | Juicer is a Weighted Finite State Transducer (WFST) based decoder for Automatic Speech Recognition (ASR). |
| Tracter | Tracter is a data flow framework. |
| Torch3vision | Common softwagre library for computer vision with machine learning algorithms. Written in simple C++, this library is based on Torch and distributed under a BSD license. |