Picture for Joanna Rownicka

Joanna Rownicka

Digital Einstein Experience: Fast Text-to-Speech for Conversational AI

Add code
Jul 21, 2021
Figure 1 for Digital Einstein Experience: Fast Text-to-Speech for Conversational AI
Figure 2 for Digital Einstein Experience: Fast Text-to-Speech for Conversational AI
Viaarxiv icon

Comparison of Speech Representations for Automatic Quality Estimation in Multi-Speaker Text-to-Speech Synthesis

Add code
Feb 28, 2020
Figure 1 for Comparison of Speech Representations for Automatic Quality Estimation in Multi-Speaker Text-to-Speech Synthesis
Figure 2 for Comparison of Speech Representations for Automatic Quality Estimation in Multi-Speaker Text-to-Speech Synthesis
Figure 3 for Comparison of Speech Representations for Automatic Quality Estimation in Multi-Speaker Text-to-Speech Synthesis
Figure 4 for Comparison of Speech Representations for Automatic Quality Estimation in Multi-Speaker Text-to-Speech Synthesis
Viaarxiv icon

Multi-scale Octave Convolutions for Robust Speech Recognition

Add code
Oct 31, 2019
Figure 1 for Multi-scale Octave Convolutions for Robust Speech Recognition
Figure 2 for Multi-scale Octave Convolutions for Robust Speech Recognition
Figure 3 for Multi-scale Octave Convolutions for Robust Speech Recognition
Figure 4 for Multi-scale Octave Convolutions for Robust Speech Recognition
Viaarxiv icon

Embeddings for DNN speaker adaptive training

Add code
Sep 30, 2019
Figure 1 for Embeddings for DNN speaker adaptive training
Figure 2 for Embeddings for DNN speaker adaptive training
Figure 3 for Embeddings for DNN speaker adaptive training
Figure 4 for Embeddings for DNN speaker adaptive training
Viaarxiv icon

Speech Replay Detection with x-Vector Attack Embeddings and Spectral Features

Add code
Sep 23, 2019
Figure 1 for Speech Replay Detection with x-Vector Attack Embeddings and Spectral Features
Figure 2 for Speech Replay Detection with x-Vector Attack Embeddings and Spectral Features
Figure 3 for Speech Replay Detection with x-Vector Attack Embeddings and Spectral Features
Figure 4 for Speech Replay Detection with x-Vector Attack Embeddings and Spectral Features
Viaarxiv icon

Analyzing deep CNN-based utterance embeddings for acoustic model adaptation

Add code
Nov 12, 2018
Figure 1 for Analyzing deep CNN-based utterance embeddings for acoustic model adaptation
Figure 2 for Analyzing deep CNN-based utterance embeddings for acoustic model adaptation
Figure 3 for Analyzing deep CNN-based utterance embeddings for acoustic model adaptation
Figure 4 for Analyzing deep CNN-based utterance embeddings for acoustic model adaptation
Viaarxiv icon