johannahom
Follow
Stars
Implementation of E2-TTS, "Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS", in Pytorch
Code for paper titled "Perception of prosodic variation for speech synthesis using an unsupervised discrete representation of F0" submitted to Speech Prosody
PyTorch implementation of VQ-VAE + WaveNet by [Chorowski et al., 2019] and VQ-VAE on speech signals by [van den Oord et al., 2017]
A set of tools for working with accent data in Mozilla's Common Voice dataset
RMarkdown documents for k-means clustering
A TextTiling-based algorithm for text segmentation (aka topic segmentation) that uses neural sentence encoders, as well as extractive summarization and semantic search applications built on top of it.
Official repository of DailyTalk: Spoken Dialogue Dataset for Conversational Text-to-Speech, ICASSP 2023
Context-based Dialogue Act Recognition using Recurrent Neural Networks
Dialog Acts SEGmentation: Tools for dialog act research
Natural Language Processing Best Practices & Examples
Leveraging BERT and c-TF-IDF to create easily interpretable topics.
DAMO-ConvAI: The official repository which contains the codebase for Alibaba DAMO Conversational AI.
Conversational text Analysis using various NLP techniques
Improving Unsupervised Dialogue Topic Segmentation with Utterance-Pair Coherence Scoring
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
This github repo is for Neurips 2021 and Interspeech 2022 papers on Non-Matching Reference based estimation of speech quality assessment.
A python library to classify dialogue tag.
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
FCTalker: Fine and Coarse Grained Context Modeling for Expressive Conversational Speech Synthesis (Accepted by ISCSLP'2024)
DiscoScore: Evaluating Text Generation with BERT and Discourse Coherence
This project contains a python implementation for the EMNLP20 paper whose title is "Centering-based Neural Coherence Modeling with Hierarchical Discourse Segments".