Pinned Repositories
speech_synthesis_objective_evaluation
Tools for evaluating the quality of synthetic speech (and particularly the ISCA SynSIG Blizzard challenge). Acoustic distance measures, synthetic speaker GMM training, wrappers for external DTW and feature extraction.
html5_audiorecorder
Audio recording for speech corpora collection, based on HTML5 running on client's browser, plus the required PHP to upload the audio data to a server.
listening_test_for_synthetic_speech_with_noise
PHP scribble for a two-part listening test for evaluating speech synthesis where noise plays some part (whether in training or in use).
multilingual_ctc_workflow_1_gather_ye_labels
Repo 1/6 for training a multilingual CTC phoneme recogniser (originally intended for pronunciation evaluation)
pilot_test_for_spoken_foreign_language
pronunciation_evaluation_scripts
64km_saattue
DeepSpeech
A TensorFlow implementation of Baidu's DeepSpeech architecture
digitala_graph_demo
rkarhila's Repositories
rkarhila/hip-cuda-gtx1050-memory-access-tests
rkarhila/lhotse-overlapping-speech
Tools for handling speech data in machine learning projects.
rkarhila/64km_saattue
rkarhila/siak-game-clients
Game clients used for research into children's foreign language learning studies in "Say It Again, kid!" project.
rkarhila/node-geoip
Native NodeJS implementation of MaxMind's GeoIP API -- works in node 0.6.3 and above, ask me about other versions
rkarhila/multilingual_ctc_workflow_1_gather_ye_labels
Repo 1/6 for training a multilingual CTC phoneme recogniser (originally intended for pronunciation evaluation)
rkarhila/DeepSpeech
A TensorFlow implementation of Baidu's DeepSpeech architecture
rkarhila/samples
WebRTC Web demos and samples
rkarhila/docker-glpi
Deploy GLPI (any version) with Docker.
rkarhila/panphon
Python package and data files for manipulating phonological segments (phones, phonemes) in terms of universal phonological features.
rkarhila/make_tfrecords_from_kaldi_ali
rkarhila/ipa-dict
Monolingual wordlists with pronunciation information in IPA
rkarhila/seriesseedfi_documents
Seriesseed.fi is a collection of standardized documents that help startups get quickly and easily off the ground.
rkarhila/hackathon-starter
A boilerplate for Node.js web applications
rkarhila/weighted-levenshtein
Weighted Levenshtein library
rkarhila/webMUSHRA
a MUSHRA compliant web audio API based experiment software
rkarhila/eesen
The official repository of the Eesen project
rkarhila/iss
Scripts for speech processing
rkarhila/pilot_test_for_spoken_foreign_language
rkarhila/digitala_graph_demo
rkarhila/node-login
A template for quickly building login systems on top of Node.js & MongoDB
rkarhila/multilingual_phoneme_classifier
Preprocessing, training and test scripts
rkarhila/pronunciation_evaluation_scripts
rkarhila/unity_to_node_audio_2_client
rkarhila/tensorflow
Computation using data flow graphs for scalable machine learning
rkarhila/fancy-mail-thingy
Let's not give too many details about this yet. But it's a web app about email classifying (by hand for now) and publishing then if they meet certain criteria.
rkarhila/vad.js
Voice activity detection in Javascript
rkarhila/spoken_language_test_pilot
A protoype for assesment of spoken language in high school finals examinations in Finnish style. Audio and video recording on browser (Chrome) and assosiated php stuff on server side to handle storing data on server.
rkarhila/speech_synthesis_objective_evaluation
Tools for evaluating the quality of synthetic speech (and particularly the ISCA SynSIG Blizzard challenge). Acoustic distance measures, synthetic speaker GMM training, wrappers for external DTW and feature extraction.
rkarhila/phone_quality_classifier
Assortment of matlab scriplets for classifying phone pronunciations by their quality.