megseekosh
Assistant Prof of Linguistics at UCLA. Director of the Speech and Cognitive Development Lab. Phonetics, vocal tracts, speech development, cochlear implants.
UCLALos Angeles
Pinned Repositories
ALICE
Automatic LInguistic Unit Count Estimator (ALICE)
audiolabel
Python library for reading and writing label files for phonetic analysis (Praat, ESPS, Wavesurfer).
babble_corpus
bucld17
Spoken word recognition of children with cochlear implants [BUCLD42]
Categorize_app_v2
GUI to chop, categorize, and annotate short audio clips from daylong audio recordings
cds-processing
code to replicate results in "Acoustic-lexical characteristics of child-directed speech between 7 and 24 months and their impact on toddlers' phonological processing"
ci-mispron
Code to replicate results from "Preschoolers rely on rich speech representations to process variable speech."
dsp_tutorials
I wanted guided tutorials on digital signal processing so I decided to create them. The result is this ebook: "Digital Signal Processing for Speech, Language, and Hearing Scientists"
everyday_speech
Code to replicate results in "Bursty, irregular speech input to preschoolers predicts vocabulary size"
vocal_tract_vowel
Triple vowel formant tracker, compute vocal tract length from formant measurements
megseekosh's Repositories
megseekosh/dsp_tutorials
I wanted guided tutorials on digital signal processing so I decided to create them. The result is this ebook: "Digital Signal Processing for Speech, Language, and Hearing Scientists"
megseekosh/Categorize_app_v2
GUI to chop, categorize, and annotate short audio clips from daylong audio recordings
megseekosh/vocal_tract_vowel
Triple vowel formant tracker, compute vocal tract length from formant measurements
megseekosh/ci-mispron
Code to replicate results from "Preschoolers rely on rich speech representations to process variable speech."
megseekosh/cds-processing
code to replicate results in "Acoustic-lexical characteristics of child-directed speech between 7 and 24 months and their impact on toddlers' phonological processing"
megseekosh/everyday_speech
Code to replicate results in "Bursty, irregular speech input to preschoolers predicts vocabulary size"
megseekosh/ALICE
Automatic LInguistic Unit Count Estimator (ALICE)
megseekosh/audiolabel
Python library for reading and writing label files for phonetic analysis (Praat, ESPS, Wavesurfer).
megseekosh/babble_corpus
megseekosh/Meas_Quechua_coartic
Measure and analyze child and adult coarticulation in Quechua via mel frequency spectra
megseekosh/ChildRecordsData
Python package for the management of day-long recordings of children.
megseekosh/Chunk-and-Label-Audio
Splits an audio file into chunks then labels each of those chunks in a .csv
megseekosh/ci_feedback
Code to replicate results in "Auditory feedback experience in phonetic development"
megseekosh/coartic-experience
megseekosh/DiViMe
ACLEW Diarization Virtual Machine (interspeech2018)
megseekosh/everyday_CI
data and code to replicate "The everyday speech environments of preschoolers with and without cochlear implants"
megseekosh/FastTrack
A Praat plugin for fast, accurate, (nearly) automatic formant-tracking
megseekosh/Homer3
MATLAB application for fNIRS data processing and visualization
megseekosh/kid_align
Forced aligners trained on largescale child speech corpora (English, Quechua)
megseekosh/megseekosh.github.io
megseekosh/Parselmouth
Praat in Python, the Pythonic way
megseekosh/Phone_emergence
Calculate and bootstrap functional load and frequency measurements over CHILDES data
megseekosh/phonlab
UC Berkeley PhonLab utilities
megseekosh/rate-normalization
Code and data to replicate modeling in "Units of processing in perceptual normalization for speaking rate"
megseekosh/ssp
Speech Signal Processing - a small collection of routines in Python to do signal processing
megseekosh/ucblingmisc
A miscellaneous collection of utilities used by UC Berkeley Linguistics.
megseekosh/Vocoder
praat script for vocoding speech
megseekosh/voice-type-classifier
A deep learning model for classifying audio frames into [SPEECH, KCHI, CHI, MAL, FEM] classes.
megseekosh/WavAugment
A library for speech data augmentation in time-domain
megseekosh/winter_storm
scripts for tutorials about Rmarkdown, ggplot2, etc. for Winter Storm 2021 at UMD