marvinlvn Goto Github PK

alice

Automatic LInguistic Unit Count Estimator (ALICE)

audiomentations

A Python library for audio data augmentation. Inspired by albumentations. Useful for machine learning.

babyslm

Behavioral probing of language acquisition models at the lexical and syntactic level

childdirectedlexicaltest

childdirectedsyntactictest

cpc2

Code for training Contrastive Predictive Coding (CPC) models from raw audio

cpc_audio

An implementation of the Contrast Predictive Coding (CPC) method to train audio features in an unsupervised fashion.

daem

Domain adaptation applied to electron microscopy segmentation

divime

ACLEW Diarization Virtual Machine

ercaguy_hello_world

"hello world" demos & templates for various languages, for beginners and experts alike, incl. gcc build commands for C & C++

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

flickr1d

A mini version of the Flickr8k written and spoken caption corpora

gpu_gmm

GPU traning of a Gaussian Mixture (with online EM)

imagetranslation-tensorflow

inftrain

Repository to train artificial infants on audiobook corpora

libri-light

dataset for lightly supervised training using the librivox audio book recordings. https://librivox.org/.

marvinlvn.github.io

A beautiful, simple, clean, and responsive Jekyll theme for academics

megamix

MeGaMix (Methods for Gaussian Mixture Models) is a python package for machine learning

paraphone

perceptimatic

Modelling code, experimental scripts, stimuli, data, and data analysis code from Millet, Jurov and Dunbar (2019), "Comparing unsupervised speech learning directly to human performance in speech perception" (Cog Sci)

platalea

Understanding visually grounded spoken language via multi-tasking

pyannote-audio

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, speaker embedding

pyannote-core

Advanced data structures for handling temporal segments with attached labels.

pyannote-metrics

A toolkit for reproducible evaluation, diagnostic, and error analysis of speaker diarization systems

sml2018-ad-data-click

In this competition, we are asked to predict whether an ad is clicked. More specifically, using the ad-click data on 2018/03/15, we have to estimate the probability of click of an ad.

vgs_xsl

This is a repository for code implementation of the paper titled "Can phones, syllables, and words emerge as side-products of cross-situational audiovisual learning? --- A computational investigation"

voice-type-classifier

A deep learning model for classifying audio frames into [SPEECH, KCHI, CHI, MAL, FEM] classes.

whisper

zerospeech2021

Zerospeech Challenge 2021: validation and evaluation software

zerospeech2021_baseline

BERT and LSTM baseline models of the ZeroSpeech Challenge 2021