41 citations · 57 across the 16 of their papers we have counts for
19 papers
Benchmarking Large Language Models for Grapheme-to-Phoneme Conversion: A Japanese Case Study
Tomoki Koriyama
Grapheme-to-phoneme (G2P) conversion is essential for controllable and robust text-to-speech, and large language models (LLMs), with broad linguistic knowledge, offer a promising a…
Exploring Pre-training Benefits on Phoneme Addition through Fine-tuning in Speech Synthesis
Masato Murata, Koichi Miyazaki, Tomoki Koriyama +1
Transfer learning is widely used for low-resource text-to-speech. When the target corpus contains phonemes unseen in pre-training, the model must expand its phoneme inventory durin…
Instantaneous Pitch Estimation via Wave-U-Net-Based Fundamental Waveform Enhancement
Junya Koguchi, Tomoki Koriyama
Instantaneous pitch estimation plays an important role in analyzing steep pitch variations such as speech prosody and singing techniques. Conventional approaches estimate instantan…
Voting-based Pitch Estimation with Temporal and Frequential Alignment and Correlation Aware Selection
Junya Koguchi, Tomoki Koriyama
The voting method, an ensemble approach for fundamental frequency estimation, is empirically known for its robustness but lacks thorough investigation. This paper provides a princi…
Speaker-Conditioned Phrase Break Prediction for Text-to-Speech with Phoneme-Level Pre-trained Language Model
Dong Yang, Yuki Saito, Takaaki Saeki +4
This paper advances phrase break prediction (also known as phrasing) in multi-speaker text-to-speech (TTS) systems. We integrate speaker-specific features by leveraging speaker emb…
Prosody Labeling with Phoneme-BERT and Speech Foundation Models
Tomoki Koriyama
This paper proposes a model for automatic prosodic label annotation, where the predicted labels can be used for training a prosody-controllable text-to-speech model. The proposed m…
Speaker-agnostic Emotion Vector for Cross-speaker Emotion Intensity Control
Masato Murata, Koichi Miyazaki, Tomoki Koriyama
Cross-speaker emotion intensity control aims to generate emotional speech of a target speaker with desired emotion intensities using only their neutral speech. A recently proposed…
Eigenvoice Synthesis based on Model Editing for Speaker Generation
Masato Murata, Koichi Miyazaki, Tomoki Koriyama +1
Speaker generation task aims to create unseen speaker voice without reference speech. The key to the task is defining a speaker space that represents diverse speakers to determine…
VAE-based Phoneme Alignment Using Gradient Annealing and SSL Acoustic Features
Tomoki Koriyama
This paper presents an accurate phoneme alignment model that aims for speech analysis and video content creation. We propose a variational autoencoder (VAE)-based alignment model i…
An Attribute Interpolation Method in Speech Synthesis by Model Merging
Masato Murata, Koichi Miyazaki, Tomoki Koriyama
With the development of speech synthesis, recent research has focused on challenging tasks, such as speaker generation and emotion intensity control. Attribute interpolation is a c…
Frame-Wise Breath Detection with Self-Training: An Exploration of Enhancing Breath Naturalness in Text-to-Speech
Dong Yang, Tomoki Koriyama, Yuki Saito
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…
Duration-aware pause insertion using pre-trained language model for multi-speaker text-to-speech
Dong Yang, Tomoki Koriyama, Yuki Saito +3
Pause insertion, also known as phrase break prediction and phrasing, is an essential part of TTS systems because proper pauses with natural duration significantly enhance the rhyth…
Structured State Space Decoder for Speech Recognition and Synthesis
Koichi Miyazaki, Masato Murata, Tomoki Koriyama
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…
UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022
Takaaki Saeki, Detai Xin, Wataru Nakata +3
We present the UTokyo-SaruLab mean opinion score (MOS) prediction system submitted to VoiceMOS Challenge 2022. The challenge is to predict the MOS values of speech samples collecte…
Multi-speaker Text-to-speech Synthesis Using Deep Gaussian Processes
Kentaro Mitsui, Tomoki Koriyama, Hiroshi Saruwatari
Multi-speaker speech synthesis is a technique for modeling multiple speakers' voices with a single model. Although many approaches using deep neural networks (DNNs) have been propo…
Utterance-level Sequential Modeling For Deep Gaussian Process Based Speech Synthesis Using Simple Recurrent Unit
Tomoki Koriyama, Hiroshi Saruwatari
This paper presents a deep Gaussian process (DGP) model with a recurrent architecture for speech sequence modeling. DGP is a Bayesian deep model that can be trained effectively wit…
JVS corpus: free Japanese multi-speaker voice corpus
Shinnosuke Takamichi, Kentaro Mitsui, Yuki Saito +3
Thanks to improvements in machine learning techniques, including deep learning, speech synthesis is becoming a machine learning task. To accelerate speech synthesis research, we ar…
Generative Moment Matching Network-based Random Modulation Post-filter for DNN-based Singing Voice Synthesis and Neural Double-tracking
Hiroki Tamaru, Yuki Saito, Shinnosuke Takamichi +2
This paper proposes a generative moment matching network (GMMN)-based post-filter that provides inter-utterance pitch variation for deep neural network (DNN)-based singing voice sy…
Sampling-based speech parameter generation using moment-matching networks
Shinnosuke Takamichi, Tomoki Koriyama, Hiroshi Saruwatari
This paper presents sampling-based speech parameter generation using moment-matching networks for Deep Neural Network (DNN)-based speech synthesis. Although people never produce ex…