Search Results for author:
Found 8 papers, 0 papers with code
Frame-Wise Breath Detection with Self-Training: An Exploration of Enhancing Breath Naturalness in Text-to-Speech
Developing Text-to-Speech (TTS) systems that can synthesize natural breath is essential for human-like voice agents but requires extensive manual annotation of breath positions in training data.
Duration-aware pause insertion using pre-trained language model for multi-speaker text-to-speech
We also leverage duration-aware pause insertion for more natural multi-speaker TTS.
Structured State Space Decoder for Speech Recognition and Synthesis
Automatic speech recognition (ASR) systems developed in recent years have shown promising results with self-attention models (e. g., Transformer and Conformer), which are replacing conventional recurrent neural networks.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Multi-speaker Text-to-speech Synthesis Using Deep Gaussian Processes
We propose a framework for multi-speaker speech synthesis using deep Gaussian processes (DGPs); a DGP is a deep architecture of Bayesian kernel regressions and thus robust to overfitting.
DNN-based Speech Synthesis Using Abundant Tags of Spontaneous Speech Corpus
In this paper, we investigate the effectiveness of using rich annotations in deep neural network (DNN)-based statistical speech synthesis.
Utterance-level Sequential Modeling For Deep Gaussian Process Based Speech Synthesis Using Simple Recurrent Unit
This paper presents a deep Gaussian process (DGP) model with a recurrent architecture for speech sequence modeling.
Generative Moment Matching Network-based Random Modulation Post-filter for DNN-based Singing Voice Synthesis and Neural Double-tracking
To address this problem, we use a GMMN to model the variation of the modulation spectrum of the pitch contour of natural singing voices and add a randomized inter-utterance variation to the pitch contour generated by conventional DNN-based singing voice synthesis.
Sampling-based speech parameter generation using moment-matching networks
To give synthetic speech natural inter-utterance variation, this paper builds DNN acoustic models that make it possible to randomly sample speech parameters.
