Pinned Repositories
ACA_DeepLearning
ACA_DL-NLP
AddressBookinTelegramBot
Attend-and-Excite
Official Implementation for "Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models" (SIGGRAPH 2023)
Bank-System
Change-Emotion
Nonparallel Emotional Speech Conversion with MUNIT Introduction This is a tensorflow implementation of my paper Nonparallel Emotional Speech Conversion. It is an end-to-end voice conversion system which can change the speaker's emotion. For example, neutral to angry, sad to happy. The model aims at generating speech with desired emotions while keeping the original liguistic content and speaker identity. It first extracts acoustic features from raw audio, then learn the mapping from source emotion to target emotion in the feature space, and finally put those features together to rebuild the waveform. In our approach, three types of features are considered:
Change-Emotions
Nonparallel Emotional Speech Conversion with MUNIT. Introduction: This is a tensorflow implementation of paper(https://arxiv.org/pdf/1811.01174.pdf) Nonparallel Emotional Speech Conversion. It is an end-to-end voice conversion system which can change the speaker's emotion. For example, neutral to angry, sad to happy. The model aims at generating speech with desired emotions while keeping the original linguistic content and speaker identity. It first extracts acoustic features from raw audio, then learn the mapping from source emotion to target emotion in the feature space, and finally put those features together to rebuild the waveform. In our approach, three types of features are considered: Features: Fundamental frequency (log F_0), converted by logarithm Gaussian normalized transformation Power envelope, converted by logarithm Gaussian normalized transformation Mel-cepstral coefficients (MCEPs), a representation of spectral envelope, trained by CycleGAN Aperiodicities (APs), directly used without modification. Dependencies: Python 3.5, Numpy 1.15, TensorFlow 1.8, LibROSA 0.6, FFmpeg 4.0, PyWorld
contactbook
gayanechilingar
Config files for my GitHub profile.
Globus
Use Weather API
gayanechilingar's Repositories
gayanechilingar/Change-Emotions
Nonparallel Emotional Speech Conversion with MUNIT. Introduction: This is a tensorflow implementation of paper(https://arxiv.org/pdf/1811.01174.pdf) Nonparallel Emotional Speech Conversion. It is an end-to-end voice conversion system which can change the speaker's emotion. For example, neutral to angry, sad to happy. The model aims at generating speech with desired emotions while keeping the original linguistic content and speaker identity. It first extracts acoustic features from raw audio, then learn the mapping from source emotion to target emotion in the feature space, and finally put those features together to rebuild the waveform. In our approach, three types of features are considered: Features: Fundamental frequency (log F_0), converted by logarithm Gaussian normalized transformation Power envelope, converted by logarithm Gaussian normalized transformation Mel-cepstral coefficients (MCEPs), a representation of spectral envelope, trained by CycleGAN Aperiodicities (APs), directly used without modification. Dependencies: Python 3.5, Numpy 1.15, TensorFlow 1.8, LibROSA 0.6, FFmpeg 4.0, PyWorld
gayanechilingar/ACA_DeepLearning
gayanechilingar/ACA_DL-NLP
gayanechilingar/AddressBookinTelegramBot
gayanechilingar/Attend-and-Excite
Official Implementation for "Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models" (SIGGRAPH 2023)
gayanechilingar/Bank-System
gayanechilingar/Change-Emotion
Nonparallel Emotional Speech Conversion with MUNIT Introduction This is a tensorflow implementation of my paper Nonparallel Emotional Speech Conversion. It is an end-to-end voice conversion system which can change the speaker's emotion. For example, neutral to angry, sad to happy. The model aims at generating speech with desired emotions while keeping the original liguistic content and speaker identity. It first extracts acoustic features from raw audio, then learn the mapping from source emotion to target emotion in the feature space, and finally put those features together to rebuild the waveform. In our approach, three types of features are considered:
gayanechilingar/contactbook
gayanechilingar/gayanechilingar
Config files for my GitHub profile.
gayanechilingar/Globus
Use Weather API
gayanechilingar/HeartBeatAnalises
Analyse heart beat data
gayanechilingar/order
gayanechilingar/Polymorphism-
gayanechilingar/Telegram
gayanechilingar/Telegram-bot-
gayanechilingar/TelegramBot
gayanechilingar/Web-page-1