NTT Communication Science Laboratories

byol-a

BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation

composing-general-audio-repr

Composing General Audio Representation by Fusing Multilayer Features of a Pre-trained Model

dcase2023_task2_baseline_ae

edge-consensus-learning

P2P Distributed deep learning framework that runs on PyTorch.

eval-audio-repr

EVAR ~ Evaluation package for Audio Representations

Generalized-Domain-Adaptation

japanese-dialog-transformers

Code for evaluating Japanese pretrained models provided by NTT Ltd.

m2d

Masked Modeling Duo: Towards a Universal Audio Pre-training Framework

msm-mae

Masked Spectrogram Modeling using Masked Autoencoders for Learning General-purpose Audio Representations

ToyADMOS2-dataset

ToyADMOS2: Another dataset of miniature-machine operating sounds for anomalous sound detection under domain shift conditions 🚗 🚃

nttcslab/japanese-dialog-transformers

Code for evaluating Japanese pretrained models provided by NTT Ltd.

nttcslab/byol-a

BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation

nttcslab/m2d

Masked Modeling Duo: Towards a Universal Audio Pre-training Framework

nttcslab/msm-mae

Masked Spectrogram Modeling using Masked Autoencoders for Learning General-purpose Audio Representations

nttcslab/dcase2023_task2_baseline_ae

nttcslab/eval-audio-repr

EVAR ~ Evaluation package for Audio Representations

nttcslab/composing-general-audio-repr

Composing General Audio Representation by Fusing Multilayer Features of a Pre-trained Model

nttcslab/edge-consensus-learning

P2P Distributed deep learning framework that runs on PyTorch.

nttcslab/ToyADMOS2-dataset

ToyADMOS2: Another dataset of miniature-machine operating sounds for anomalous sound detection under domain shift conditions 🚗 🚃

nttcslab/dcase2023_task2_evaluator

nttcslab/Learning-with-Selective-Forgetting

This is an official PyTorch impelementation of our paper "Learning with Selective Forgetting" (IJCAI21).

nttcslab/dcase2024_task2_evaluator

nttcslab/japanese-long-term-chat

nttcslab/soundsil-ds

nttcslab/deep-sound-field-denoiser

nttcslab/rope

Code of the paper "Reflectance-oriented probabilistic equalization for image enhancement" published in ICASSP 2021.

nttcslab/audio-diff-caps

nttcslab/cone

Official PyTorch Implementation of "Deep Quantigraphic Image Enhancement via Comparametric Equations" (ICASSP2023)

nttcslab/DET_AFP

This is the official PyTorch impelementation of our paper "Robustizing Object Detection Networks Using Augmented Feature Pooling" (ACCV2022, Oral).

nttcslab/adaptive-leveling-BO

nttcslab/fast-ecp-ecn

An implementation of "A Fast and Exact Evaluation Algorithm for the Expected Number of Connected Nodes: an Enhanced Network Reliability Measure" in IEEE INFOCOM 2023.

nttcslab/improved_sfda

nttcslab/time-considerable-dialogue-model

This repository provides the information necessary to evaluate time-considerable dialogue models.

nttcslab/COCO-ROT

This is the official PyTorch impelementation of our paper "Robustizing Object Detection Networks Using Augmented Feature Pooling" (ACCV2022, Oral).

nttcslab/scale-wise-unrel

An implementation of "Exact and Efficient Network Reliability Evaluation per Outage Scale" in IEEE ICC 2023.

nttcslab/collision-probability-matching

nttcslab/compdp-counting

An implementation of "CompDP: A Framework for Simultaneous Subgraph Counting under Connectivity Constraints" in SEA 2023.

nttcslab/KmeansDocData

Accelerating K-means clustering for document data sets with an architecture-friendly pruning method

nttcslab/layered-param-perturb

nttcslab/mppvae

An implementation of "Marked point process variational autoencoder with applications to unsorted spiking activities"