Search Results for author: Hiroshi Saruwatari

Found 30 papers, 6 papers with code

jaCappella Corpus: A Japanese a Cappella Vocal Ensemble Corpus

1 code implementation29 Nov 2022 Tomohiko Nakamura, Shinnosuke Takamichi, Naoko Tanji, Satoru Fukayama, Hiroshi Saruwatari

These songs were arranged from out-of-copyright Japanese children's songs and have six voice parts (lead vocal, soprano, alto, tenor, bass, and vocal percussion).

Vocal ensemble separation

Hyperbolic Timbre Embedding for Musical Instrument Sound Synthesis Based on Variational Autoencoders

no code implementations27 Sep 2022 Futa Nakashima, Tomohiko Nakamura, Norihiro Takamune, Satoru Fukayama, Hiroshi Saruwatari

In this paper, we propose a musical instrument sound synthesis (MISS) method based on a variational autoencoder (VAE) that has a hierarchy-inducing latent space for timbre.

Multi-Task Adversarial Training Algorithm for Multi-Speaker Neural Text-to-Speech

no code implementations26 Sep 2022 Yusuke Nakai, Yuki Saito, Kenta Udagawa, Hiroshi Saruwatari

A conventional generative adversarial network (GAN)-based training algorithm significantly improves the quality of synthetic speech by reducing the statistical difference between natural and synthetic speech.

Human-in-the-loop Speaker Adaptation for DNN-based Multi-speaker TTS

no code implementations21 Jun 2022 Kenta Udagawa, Yuki Saito, Hiroshi Saruwatari

With a conventional speaker-adaptation method, a target speaker's embedding vector is extracted from his/her reference speech using a speaker encoder trained on a speaker-discriminative task.

Acoustic Modeling for End-to-End Empathetic Dialogue Speech Synthesis Using Linguistic and Prosodic Contexts of Dialogue History

no code implementations16 Jun 2022 Yuto Nishimura, Yuki Saito, Shinnosuke Takamichi, Kentaro Tachibana, Hiroshi Saruwatari

To train the empathetic DSS model effectively, we investigate 1) a self-supervised learning model pretrained with large speech corpora, 2) a style-guided training using a prosody embedding of the current utterance to be predicted by the dialogue context embedding, 3) a cross-modal attention to combine text and speech modalities, and 4) a sentence-wise embedding to achieve fine-grained prosody modeling rather than utterance-wise modeling.

Self-Supervised Learning Speech Synthesis +1

Region-to-region kernel interpolation of acoustic transfer function with directional weighting

no code implementations5 May 2022 Juliano G. C. Ribeiro, Shoichi Koyama, Hiroshi Saruwatari

A method of interpolating the acoustic transfer function (ATF) between regions that takes into account both the physical properties of the ATF and the directionality of region configurations is proposed.

Hyperparameter Optimization

STUDIES: Corpus of Japanese Empathetic Dialogue Speech Towards Friendly Voice Agent

no code implementations28 Mar 2022 Yuki Saito, Yuto Nishimura, Shinnosuke Takamichi, Kentaro Tachibana, Hiroshi Saruwatari

We describe our methodology to construct an empathetic dialogue speech corpus and report the analysis results of the STUDIES corpus.

Spatial active noise control based on individual kernel interpolation of primary and secondary sound fields

no code implementations10 Feb 2022 Kazuyuki Arikawa, Shoichi Koyama, Hiroshi Saruwatari

A spatial active noise control (ANC) method based on the individual kernel interpolation of primary and secondary sound fields is proposed.

Differentiable Digital Signal Processing Mixture Model for Synthesis Parameter Extraction from Mixture of Harmonic Sounds

no code implementations1 Feb 2022 Masaya Kawamura, Tomohiko Nakamura, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, Kazunobu Kondo

A differentiable digital signal processing (DDSP) autoencoder is a musical sound synthesizer that combines a deep neural network (DNN) and spectral modeling synthesis.

Audio Source Separation

Low-Latency Incremental Text-to-Speech Synthesis with Distilled Context Prediction Network

no code implementations22 Sep 2021 Takaaki Saeki, Shinnosuke Takamichi, Hiroshi Saruwatari

Although this method achieves comparable speech quality to that of a method that waits for the future context, it entails a huge amount of processing for sampling from the language model at each time step.

Knowledge Distillation Language Modelling +2

Binaural rendering from microphone array signals of arbitrary geometry

no code implementations15 Sep 2021 Naoto Iijima, Shoichi Koyama, Hiroshi Saruwatari

To reproduce binaural signals from microphone array recordings at a remote location, a spherical microphone array is generally used for capturing a soundfield.

Sampling-Frequency-Independent Audio Source Separation Using Convolution Layer Based on Impulse Invariant Method

1 code implementation10 May 2021 Koichi Saito, Tomohiko Nakamura, Kohei Yatabe, Yuma Koizumi, Hiroshi Saruwatari

Audio source separation is often used as preprocessing of various applications, and one of its ultimate goals is to construct a single versatile model capable of dealing with the varieties of audio signals.

Audio Source Separation Music Source Separation

HumanACGAN: conditional generative adversarial network with human-based auxiliary classifier and its evaluation in phoneme perception

no code implementations8 Feb 2021 Yota Ueda, Kazuki Fujii, Yuki Saito, Shinnosuke Takamichi, Yukino Baba, Hiroshi Saruwatari

A DNN-based generator is trained using a human-based discriminator, i. e., humans' perceptual evaluations, instead of the GAN's DNN-based discriminator.

Multi-speaker Text-to-speech Synthesis Using Deep Gaussian Processes

no code implementations7 Aug 2020 Kentaro Mitsui, Tomoki Koriyama, Hiroshi Saruwatari

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.

Gaussian Processes Speech Synthesis +1

Utterance-level Sequential Modeling For Deep Gaussian Process Based Speech Synthesis Using Simple Recurrent Unit

no code implementations22 Apr 2020 Tomoki Koriyama, Hiroshi Saruwatari

This paper presents a deep Gaussian process (DGP) model with a recurrent architecture for speech sequence modeling.

Speech Synthesis

Time-Domain Audio Source Separation Based on Wave-U-Net Combined with Discrete Wavelet Transform

1 code implementation28 Jan 2020 Tomohiko Nakamura, Hiroshi Saruwatari

With this belief, focusing on the fact that the DWT has an anti-aliasing filter and the perfect reconstruction property, we design the proposed layers.

Audio Source Separation Music Source Separation

HumanGAN: generative adversarial network with human-based discriminator and its evaluation in speech perception modeling

no code implementations25 Sep 2019 Kazuki Fujii, Yuki Saito, Shinnosuke Takamichi, Yukino Baba, Hiroshi Saruwatari

To model the human-acceptable distribution, we formulate a backpropagation-based generator training algorithm by regarding human perception as a black-boxed discriminator.

V2S attack: building DNN-based voice conversion from automatic speaker verification

no code implementations5 Aug 2019 Taiki Nakamura, Yuki Saito, Shinnosuke Takamichi, Yusuke Ijima, Hiroshi Saruwatari

The experimental evaluation compares converted voices between the proposed method that does not use the targeted speaker's voice data and the standard VC that uses the data.

Automatic Speech Recognition Speaker Verification +2

DNN-based Speaker Embedding Using Subjective Inter-speaker Similarity for Multi-speaker Modeling in Speech Synthesis

no code implementations19 Jul 2019 Yuki Saito, Shinnosuke Takamichi, Hiroshi Saruwatari

Although conventional DNN-based speaker embedding such as a $d$-vector can be applied to multi-speaker modeling in speech synthesis, it does not correlate with the subjective inter-speaker similarity and is not necessarily appropriate speaker representation for open speakers whose speech utterances are not included in the training data.

Speech Synthesis

Generative Moment Matching Network-based Random Modulation Post-filter for DNN-based Singing Voice Synthesis and Neural Double-tracking

no code implementations9 Feb 2019 Hiroki Tamaru, Yuki Saito, Shinnosuke Takamichi, Tomoki Koriyama, Hiroshi Saruwatari

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.

Phase reconstruction from amplitude spectrograms based on von-Mises-distribution deep neural network

2 code implementations10 Jul 2018 Shinnosuke Takamichi, Yuki Saito, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari

This paper presents a deep neural network (DNN)-based phase reconstruction from amplitude spectrograms.

Sound Audio and Speech Processing

JSUT corpus: free large-scale Japanese speech corpus for end-to-end speech synthesis

no code implementations28 Oct 2017 Ryosuke Sonobe, Shinnosuke Takamichi, Hiroshi Saruwatari

Thanks to improvements in machine learning techniques including deep learning, a free large-scale speech corpus that can be shared between academic institutions and commercial companies has an important role.

BIG-bench Machine Learning Speech Synthesis

Statistical Parametric Speech Synthesis Incorporating Generative Adversarial Networks

4 code implementations23 Sep 2017 Yuki Saito, Shinnosuke Takamichi, Hiroshi Saruwatari

In the proposed framework incorporating the GANs, the discriminator is trained to distinguish natural and generated speech parameters, while the acoustic models are trained to minimize the weighted sum of the conventional minimum generation loss and an adversarial loss for deceiving the discriminator.

Speech Synthesis Voice Conversion

Sampling-based speech parameter generation using moment-matching networks

no code implementations12 Apr 2017 Shinnosuke Takamichi, Tomoki Koriyama, Hiroshi Saruwatari

To give synthetic speech natural inter-utterance variation, this paper builds DNN acoustic models that make it possible to randomly sample speech parameters.

Speech Synthesis

Voice Conversion Using Sequence-to-Sequence Learning of Context Posterior Probabilities

no code implementations10 Apr 2017 Hiroyuki Miyoshi, Yuki Saito, Shinnosuke Takamichi, Hiroshi Saruwatari

Conventional VC using shared context posterior probabilities predicts target speech parameters from the context posterior probabilities estimated from the source speech parameters.

speech-recognition Speech Recognition +2

Cannot find the paper you are looking for? You can Submit a new open access paper.