IT Wiki

Character Error Rate

CTC

Computer vision

Document AI

Handwriting recognition

PDF

Text-to-Speech

Speech synthesis

Grapheme-to-Phoneme

Phoneme

Prosody

Acoustic model

Vocoder

SSML

Voice cloning

Audio generation

Speech-to-Text

Automatic Speech Recognition

Voice Activity Detection

Speaker diarization

Word Error Rate

Transcription

Beam search

Speech processing

Generative Adversarial Network

Discriminator

Latent space

Mode collapse

DCGAN

Conditional GAN

Deepfake

Convolutional Neural Network

Receptive field

Object detection

Recurrent Neural Network

Hidden state

Backpropagation Through Time

Vanishing gradient

Exploding gradient

Bidirectional RNN

Long Short-Term Memory

Cell state

Forget gate

Input gate

Output gate

Bidirectional LSTM

Gated Recurrent Unit

Update gate