Search Results for author:
Found 6 papers, 2 papers with code
Multilingual and Fully Non-Autoregressive ASR with Large Language Model Fusion: A Comprehensive Study
In the era of large models, the autoregressive nature of decoding often results in latency serving as a significant bottleneck.
UserLibri: A Dataset for ASR Personalization Using Only Text
We experiment on a user-clustered LibriSpeech corpus, supplemented with personalized text-only data for each user from Project Gutenberg.
Prosody Transfer in Neural Text to Speech Using Global Pitch and Loudness Features
This paper presents a simple yet effective method to achieve prosody transfer from a reference speech signal to synthesized speech.
Pay ``Attention'' to your Context when Classifying Abusive Language
The goal of any social media platform is to facilitate healthy and meaningful interactions among its users.
Context-Aware Attention for Understanding Twitter Abuse
The original goal of any social media platform is to facilitate users to indulge in healthy and meaningful conversations.
A Hybrid Variational Autoencoder for Collaborative Filtering
Our approach combines movie embeddings (learned from a sibling VAE network) with user ratings from the Movielens 20M dataset and applies it to the task of movie recommendation.
