Name: Shammur Absar
Type: User
Company: QCRI
Bio: Interested in analyzing and understanding human conversation. Main focus: speech overlaps, turn-takings, speech discourse, code-switching, explainability.
Blog: http://shammur.one/
Shammur Absar 's Projects
This is the R script and the table used for the gender analysis of the speech corpora available on OpenSLR.
Dataset of 57 mock medical primary care consultations: audio, consultation notes, human utterance-level transcripts.
🐙 Guides, papers, lecture, notebooks and resources for prompt engineering
Python interface to the WebRTC Voice Activity Detector
Python Audio Analysis Library: Feature Extraction, Classification, Segmentation and Applications
Manipulate audio with a simple and easy high level interface
A Python wrapper for Kaldi
Some Jupyter notebooks about audio signal processing with Python
A simple VAD pipeline based on pyAudioAnalysis
Deep Learning Utilities for Audio Segmentation
The PreTENS shared task hosted at SemEval 2022 aims at focusing on semantic competence with specific attention on the evaluation of language models with respect to the recognition of appropriate taxonomic relations between two nominal arguments (i.e. cases where one is a supercategory of the other, or in extensional terms, one denotes a superset of the other).
kaldi-free Speaker recognition toolkit using tensorflow
Python implementation of Sparse Subspace Clustering algorithm.
On going work ..
Think DSP: Digital Signal Processing in Python, by Allen B. Downey.
tmux source code
A simple JSON API framework based on Tornado
Speech Emotion Classification with novel Parallel CNN-Transformer model built with PyTorch, plus thorough explanations of CNNs, Transformers, and everything in between
🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.
Model explainability that works seamlessly with 🤗 transformers. Explain your transformers model in just 2 lines of code.
Voice Activity Detector in Python
🔊 A comprehensive list of open-source datasets for voice and sound computing (50+ datasets).
♂️♀️ Detect a person's gender from a voice file. Achieves 90.7% +/- 1.3% accuracy.
Attempt at tracking states of the arts and recent results (bibliography) on speech recognition.
1st place solution to Kaggle's 2018 YouTube-8M Video Understanding Challenge