NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment

ICASSP 2023-2024 Papers: A complete collection of influential and exciting research papers from the ICASSP 2023-24 conferences. Explore the latest advancements in acoustics, speech and signal processing. Code included. Star the repository to support the advancement of audio and signal processing!

ICASSP 2022: "Text2Video: text-driven talking-head video synthesis with phonetic dictionary".

Code & Data for "Tabular Transformers for Modeling Multivariate Time Series" (ICASSP, 2021)

Reading list for research topics in Sound AI

[ICASSP 2023] Official Tensorflow implementation of "Temporal Modeling Matters: A Novel Temporal Emotional Modeling Approach for Speech Emotion Recognition".

This repository contains code to replicate results from the ICASSP 2020 paper "StarGAN for Emotional Speech Conversion: Validated by Data Augmentation of End-to-End Emotion Recognition".

The repository provides links to collections of influential and interesting research papers from top AI conferences, with open-source code to promote reproducibility and provide detailed implementation insights beyond the scope of the article. Stay up to date with the latest advances in AI research!

ChunkFormer: Masked Chunking Conformer For Long-Form Speech Transcription

ICASSP2017: End-to-end joint learning of natural language understanding and dialogue manager

This repository contains the code for the paper "voc2vec: A Foundation Model for Non-Verbal Vocalization", accepted at ICASSP 2025.

[ICASSP 2024] Official implementation of our paper "Contrastive Deep Nonnegative Matrix Factorization for Community Detection"

Face Recognition in real-world images [ICASSP 2017]

This repository is the implementation of the HiPAMA architecture, introduced in the paper, Hierarchical Pronunciation Assessment with Multi-Aspect Attention (ICASSP 2023).

[ICASSP19] An Interaction-aware Attention Network for Speech Emotion Recognition in Spoken Dialogs

This repository provides LaTeX templates for academic papers, you can select the appropriate template for your target conference or journal by switching branches. Each branch corresponds to a specific publication venue and follows its official formatting requirements.|本项目提供多种学术论文的 LaTeX 模板，可通过切换分支选择对应的会议或期刊模板。每个分支均针对特定投稿场景设计，并遵循相应的官方排版规范。

Official PyTorch implementation of A Quaternion-Valued Variational Autoencoder (QVAE).

SERAB: a multi-lingual benchmark for speech emotion recognition

[ICASSP 2025 Oral] ImageFlowNet: Forecasting Multiscale Image-Level Trajectories of Disease Progression with Irregularly-Sampled Longitudinal Medical Images

ICASSP 2019 official Latex template

Speaker-aware CTC (SACTC) for multi-talker overlapped speech recognition.

ICASSP 2021: Scene Completeness-Aware Lidar Depth Completion for Driving Scenario

Continual Learning Benchmark for Spoken Keyword Spotting

2D residual U-Net (ResUNet) and a lead combiner (LC) for 12-lead ECG Abnormality Classification

The official implementation for IEEE-ICASSP 2024 paper "Flare-Free Vision: Empowering Uformer with Depth Insights"

[ICASSP 2025 Oral] ImageFlowNet: Forecasting Multiscale Image-Level Trajectories of Disease Progression with Irregularly-Sampled Longitudinal Medical Images

A regularized version of RBM for unsupervised feature selection.

Python Implementation for Directional Sparse Filtering with Tensorflow/Keras

Official repo for "Audio-Visual Speech Recognition In-the-Wild: Multi-Angle Vehicle Cabin Corpus and Attention-based Method" in ICASSP 2024

code for the paper: PRIVACY-PRESERVING DEEP LEARNING: LEVERAGING DEFORMABLE OPERATORS FOR SECURE TASK LEARNING