entn-at Goto Github PK

lattice_combination

Lattice combination algorithm to combine inaccurate transcripts with hypothesis lattices

laughter-synthesis

Official implementation of the paper "Laughter Synthesis using Pseudo Phonetic Tokens with a Large-scale In-the-wild Laughter Corpus" accepted by INTERSPEECH 2023.

layerwise-analysis

Layer-wise analysis of self-supervised pre-trained speech representations

layout-parser

A Unified Toolkit for Deep Learning Based Document Image Analysis

lclda

local classific linear discriminant analysis backend for speaker verification

lcnn

A TensorFlow implementation of light convolutional neural network (LCNN)

leaf-audio

leaf-audio-pytorch

Pytorch port of Google Research's LEAF Audio paper

leaf-pytorch

PyTorch implementation of the LEAF audio frontend

leap_diarization

LEAP Diarization System for the Second DIHARD Challenge

learningtocompare-tensorflow

Tensorflow implementation for paper: Learning to Compare: Relation Network for Few-Shot Learning.

legacy_straight

A vocoder framework which had been widely used in research community since 1999.

lexicon_discovery

Source code for "Unsupervised Lexicon Discovery from Acoustic Input ", Lee et al, 2015 TACL

lhotse

libbaresip-android

libbaresip for Android

libfvad

Voice activity detection (VAD) library, based on WebRTC's VAD engine

libgvps

Generic Viterbi Path Searcher

libllsm2

Low Level Speech Model (version 2) for high quality speech analysis-synthesis

liblrhsmm

Left-to-right Hidden Semi-Markov Model implementation in C

libphonenumber

Google's common Java, C++ and JavaScript library for parsing, formatting, and validating international phone numbers.

libpyin

pYIN implementation for fundamental frequency estimation

libri-light

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

libriheavy

Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context

librittslabel

Alignment files of LibriTTS.

lidbox

End-to-end spoken language identification with TensorFlow 2

light-sernet

Light-SERNet: A lightweight fully convolutional neural network for speech emotion recognition

lightspeech

A Light, Fast and Robust Speech Synthesis.

lightspeech-1

LightSpeech: Lightweight and Fast Text to Speech with Neural Architecture Search

lightweight_spkr_anon

Lightweight speaker anonymization [IEEE SLT2021]

lilcom

Small compression utility