Speech, Language, and Deep Learning Lab
The source code of some of the projects conducted in Joseph Keshet's Research Lab.
Pinned Repositories
AutoAligner
Trainable algorithm for accurate force alignment
AutoPhonemeClassifier
Multiclass Phoneme Classifier trained at the frame level
AutoVowelDuration
Automatic Measurement of Vowel Duration for Consonant Vowel Consonant (CVC) sound files
DeepFormants
Formant Tracking & Estimation
DeepPhoneticToolsTutorial
Tutorial on {Deep} Phonetic Tools given in BigPhon @ LabPhon15
Dr.VOT
Dr.VOT is an a software package for automatic measurement of voice onset time (VOT).
FormantsTracker
scaler_gan
speech_yolo
SpeechYOLO Interspeech 2019
ssl_diarization
Self-supervised Speaker Diarization Interspeech 2022 Implementation
Speech, Language, and Deep Learning Lab's Repositories
MLSpeech/DeepFormants
Formant Tracking & Estimation
MLSpeech/speech_yolo
SpeechYOLO Interspeech 2019
MLSpeech/Dr.VOT
Dr.VOT is an a software package for automatic measurement of voice onset time (VOT).
MLSpeech/DeepPhoneticToolsTutorial
Tutorial on {Deep} Phonetic Tools given in BigPhon @ LabPhon15
MLSpeech/FormantsTracker
MLSpeech/ssl_diarization
Self-supervised Speaker Diarization Interspeech 2022 Implementation
MLSpeech/AutoPhonemeClassifier
Multiclass Phoneme Classifier trained at the frame level
MLSpeech/AutoVowelDuration
Automatic Measurement of Vowel Duration for Consonant Vowel Consonant (CVC) sound files
MLSpeech/scaler_gan
MLSpeech/AutoPreaspiration
A software package for automatic extraction of pre-aspiration from speech segments in audio files, using a trainable algorithm.
MLSpeech/GradSeg
MLSpeech/AutoVOT
Trainable algorithm for automatic measurement of voice onset time
MLSpeech/DDKtor
MLSpeech/DeepVOT
Automatic Measurement of Voice Onset Time (VOT) using Deep Recurrent Neural Networks
MLSpeech/DeepWDM
Recurrent Neural Networks for Word Duration Measurement
MLSpeech/distributed_random_features_svm
a distributed implementation of SVM using random features
MLSpeech/DSegKNN
MLSpeech/WatermarkNN
Watermarking Deep Neural Networks (USENIX 2018)
MLSpeech/.github
MLSpeech/FixedClassificationLayer
MLSpeech/MLSpeech.github.io
Machine learning-based tools for fine grained phonetic measurements
MLSpeech/semantic_OOD
MLSpeech/CRP
Training with constant perturbations against adversarial attacks.
MLSpeech/DIFFAR
Denoising Diffusion Autoregressive Model for Raw Speech Waveform Generation
MLSpeech/Image-Captioning
This project implements the paper: "Show, Attend and Tell: Neural Image Caption Generation with Visual Attention"
MLSpeech/percept_sim
MLSpeech/PiMOD
Pitch Estimation by Multiple Octave Decoders
MLSpeech/WatermarkVerification
MLSpeech/Whisper_denoiser
MLSpeech/WhisperDenoiser