c3imaging Goto Github PK

biometrics

c3imaging.github.io

Github Page for C3Imaging

childasr_w2v2

This repository provides trained checkpoints for finetuning across different child speech datasets for improving the performance on ASR for child speech. .

childtts

This repository contains synthetic TTS generated audio files for presenting our research work

child_asr_conformer

A comparative analysis between Conformer Transducer, Whisper and Wav2vec2 for improving the child speech recognition

child_tts_fastpitch

Fastpitch text-to-speech (TTS) model for generating high-quality synthetic child speech. This study uses the transfer learning training pipeline. The approach involved finetuning a multi-speaker TTS model to work with child speech. We use the publicly available MyST dataset (55 hours) for our finetuning experiments.

deep-learning-techniques

image-depth-analysis

security-and-block-chain

speech-augmentation

syntheticheadpose

whisper_child_asr

whisper_non_native_child_asr