speech-classification

It is a full-fetched web application.Based on sentiment classification, by using nltk library it predicts that a speech is how much toxic, sever toxic, insult, obscene, threat.

This repository contains code for all assignments in the Multimedia Computing and Applications (CSE563) course.

Fall 2021 Introduction to Deep Learning - Homework 3 Part 2 (RNN-based phoneme recognition)

Speech Classification using Continuous Attention Mechanisms

Code for the AAAI 2022 paper "SSAST: Self-Supervised Audio Spectrogram Transformer".

Transformer-based model for Speech Emotion Recognition(SER) - implemented by Pytorch

Official Implementation of the work "Audio Mamba: Bidirectional State Space Model for Audio Representation Learning"

This project aims to perform Emotion Recognition in Speech using Deep Neural Networks (DNNs)

This repository contains the code for the INTERSPEECH2025 paper: "Speech and Text Foundation Models for Depression Detection: Cross-Task and Cross-Language Evaluation"

Detecting Speed and Tempo Alterations in Speech Recordings

RU directed speech classifier (ruElectra, synthetic ASR noise)

Code for audio-based autism spectrum disorder (ASD) classification using Transformer models, machine learning baselines, and SHAP analysis.

Efficient few-shot audio classification with contrastive fine-tuning.

Detects real vs. AI-generated (TTS) Khmer speech using a fine-tuned wav2vec2 model. Full data-to-demo pipeline with a Streamlit app.

Academic course project for spoken language identification across 22 Indian languages using W2V-BERT, PyTorch, and audio augmentation.

A multi-modal acoustic-aware fusion architecture for dysarthria detection and severity classification. Combines LoRA-adapted wav2vec 2.0 with classical MFCC features in a dual-pathway network, grounding foundation models in deterministic acoustic physics for clinical interpretability.