Search Results for author:
Found 6 papers, 1 papers with code
Digital Einstein Experience: Fast Text-to-Speech for Conversational AI
We describe our approach to create and deliver a custom voice for a conversational AI use-case.
Comparison of Speech Representations for Automatic Quality Estimation in Multi-Speaker Text-to-Speech Synthesis
Our NN predicts MOS with a high correlation to human judgments.
Multi-scale Octave Convolutions for Robust Speech Recognition
We propose a multi-scale octave convolution layer to learn robust speech representations efficiently.
Embeddings for DNN speaker adaptive training
In this work, we investigate the use of embeddings for speaker-adaptive training of DNNs (DNN-SAT) focusing on a small amount of adaptation data per speaker.
Speech Replay Detection with x-Vector Attack Embeddings and Spectral Features
Our system used convolutional neural networks (CNNs) and a representation of the speech audio that combined x-vector attack embeddings with signal processing features.
Analyzing deep CNN-based utterance embeddings for acoustic model adaptation
We analyze the representations learned by deep CNNs and compare them with deep neural network (DNN) representations and i-vectors, in the context of acoustic model adaptation.
