Uncategorized

• Uncategorized

  • Carmel - state toolkit, EM and Bayesian (Gibbs sampling) training for FST and context-free derivation forests/
  • IBM Watson Alchemy Language
  • Microsoft Cognitive Service
  • Aylien
  • Categorial semiring
  • dk.brics.automaton
  • fsm2.0 - way composition
  • MIT FST Toolkit
  • OpenFst - state transducers (FSTs).
  • SFST - Stuttgart Finite State Transducer Tools
  • Treba - line tool for training, decoding, and calculating with weighted (probabilistic) finite state automata (PFSA) and Hidden Markov Models (HMMs)."
  • Bayesian Recurrent Neural Network for Language Modeling
  • Berkeley LM
  • CSLM - source software which implements the so-called continuous space language model.
  • lwlm
  • Maximum Entropy Modeling
  • Maximum entropy language models: SRILM extension - gram features are supported"
  • MSRLM - model tool is used to build language models from large amounts of data. It supports modified absolute discounting and Kneser-Ney smoothing."
  • OpenGrm
  • RandLM
  • RNNLM
  • Refr - ranking framework from the Johns-Hopkins workshop on confusion language modelling.
  • rwthlm - term memory neural networks). The software was written by Martin Sundermeyer.
  • SRILM - free for commerical use.
  • AaltoASR
  • Bavieca
  • Julius - performance, two-pass large vocabulary continuous speech recognition (LVCSR) decoder software for speech-related researchers and developers."
  • OpenDcd
  • Phonetisaurus
  • SCARF: A Segmental CRF Toolkit for Speech Recognition
  • trainc - dependency transducers (Interspeech best paper).
  • RASR - The RWTH Aachen University Speech Recognition System
  • An Interactive Source Separation Editor - source, freely available, cross-platform audio editing tool that allows a user to perform source separation by painting on time-frequency visualisations of sound."
  • Matlab Audio Processing Examples
  • SAcC - Subband Autocorrelation Classification Pitch Tracker - robust pitch tracking by classifying the autocorrelations of a set of subbands using an MLP neural network."
  • HTS - based speech synthesis
  • TED-LIUM Corpus - LIUM corpus was made from audio talks and their transcriptions available on the TED website.
  • Berkeley Aligner
  • Jane - of-the-art techniques for phrase-based and hierarchical phrase-based machine translation."
  • Joshua
  • zmert
  • BIDData - scale exploratory data analysis. Its sister library BIDMach implements the machine learning layer.
  • libFM: Factorization Machine Library
  • Cafee - Really active deep learning toolkit with support for cuDNN and lots of other backends.
  • cuDNN - Deep neural network from Nvidia with paper [here](http://arxiv.org/pdf/1410.0759.pdf). [Torch 7 has support for cuDnn](https://github.com/soumith/cudnn.torch) and [here](https://github.com/hannes-brt/cudnn-python-wrappers) are some Python wrappers.
  • CURRENNT - Munich Open-Source CUDA RecurREnt Neural Network Toolkit described in this [paper](http://www.mmk.ei.tum.de/publ/pdf/14/14wen7.pdf)
  • Glove
  • Between One and Zero
  • Language Log
  • LingPipe Blog
  • Spoken Language Processing
  • Foundations of Data Science
  • Introduction to Matrix Methods and Applications
  • Rosette
  • Matlab Audio Processing Examples
  • IBM Watson Alchemy Language
  • Neural Probabilistic Language Model Toolkit
  • IBM Watson Alchemy Language
  • Cafee - Really active deep learning toolkit with support for cuDNN and lots of other backends.
  • Berkeley Aligner