41 citations · 100 across the 25 of their papers we have counts for
26 papers
J-CHAT: Japanese Large-scale Spoken Dialogue Corpus for Spoken Dialogue Language Modeling
Wataru Nakata, Kentaro Seki, Hitomi Yanaka +3
Spoken dialogue is essential for human-AI interactions, providing expressive capabilities beyond text. Developing effective spoken dialogue systems (SDSs) requires large-scale, hig…
Spatial Voice Conversion: Voice Conversion Preserving Spatial Information and Non-target Signals
Kentaro Seki, Shinnosuke Takamichi, Norihiro Takamune +3
This paper proposes a new task called spatial voice conversion, which aims to convert a target voice while preserving spatial information and non-target signals. Traditional voice…
Noise-Robust Voice Conversion by Conditional Denoising Training Using Latent Variables of Recording Quality and Environment
Takuto Igarashi, Yuki Saito, Kentaro Seki +4
We propose noise-robust voice conversion (VC) which takes into account the recording quality and environment of noisy source speech. Conventional denoising training improves the no…
SRC4VC: Smartphone-Recorded Corpus for Voice Conversion Benchmark
Yuki Saito, Takuto Igarashi, Kentaro Seki +4
We present SRC4VC, a new corpus containing 11 hours of speech recorded on smartphones by 100 Japanese speakers. Although high-quality multi-speaker corpora can advance voice conver…
Building speech corpus with diverse voice characteristics for its prompt-based representation
Aya Watanabe, Shinnosuke Takamichi, Yuki Saito +3
In text-to-speech synthesis, the ability to control voice characteristics is vital for various applications. By leveraging thriving text prompt-based generation techniques, it shou…
JVNV: A Corpus of Japanese Emotional Speech with Verbal Content and Nonverbal Expressions
Detai Xin, Junfeng Jiang, Shinnosuke Takamichi +3
We present the JVNV, a Japanese emotional speech corpus with verbal content and nonverbal vocalizations whose scripts are generated by a large-scale language model. Existing emotio…
Coco-Nut: Corpus of Japanese Utterance and Voice Characteristics Description for Prompt-based Control
Aya Watanabe, Shinnosuke Takamichi, Yuki Saito +3
In text-to-speech, controlling voice characteristics is important in achieving various-purpose speech synthesis. Considering the success of text-conditioned generation, such as tex…
HumanDiffusion: diffusion model using perceptual gradients
Yota Ueda, Shinnosuke Takamichi, Yuki Saito +2
We propose {\it HumanDiffusion,} a diffusion model trained from humans' perceptual gradients to learn an acceptable range of data for humans (i.e., human-acceptable distribution).…
ChatGPT-EDSS: Empathetic Dialogue Speech Synthesis Trained from ChatGPT-derived Context Word Embeddings
Yuki Saito, Shinnosuke Takamichi, Eiji Iimori +2
We propose ChatGPT-EDSS, an empathetic dialogue speech synthesis (EDSS) method using ChatGPT for extracting dialogue context. ChatGPT is a chatbot that can deeply understand the co…
CALLS: Japanese Empathetic Dialogue Speech Corpus of Complaint Handling and Attentive Listening in Customer Center
Yuki Saito, Eiji Iimori, Shinnosuke Takamichi +2
We present CALLS, a Japanese speech corpus that considers phone calls in a customer center as a new domain of empathetic spoken dialogue. The existing STUDIES corpus covers only em…
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…
Mid-attribute speaker generation using optimal-transport-based interpolation of Gaussian mixture models
Aya Watanabe, Shinnosuke Takamichi, Yuki Saito +2
In this paper, we propose a method for intermediating multiple speakers' attributes and diversifying their voice characteristics in ``speaker generation,'' an emerging task that ai…
Multi-Task Adversarial Training Algorithm for Multi-Speaker Neural Text-to-Speech
Yusuke Nakai, Yuki Saito, Kenta Udagawa +1
We propose a novel training algorithm for a multi-speaker neural text-to-speech (TTS) model based on multi-task adversarial training. A conventional generative adversarial network…
Human-in-the-loop Speaker Adaptation for DNN-based Multi-speaker TTS
Kenta Udagawa, Yuki Saito, Hiroshi Saruwatari
This paper proposes a human-in-the-loop speaker-adaptation method for multi-speaker text-to-speech. With a conventional speaker-adaptation method, a target speaker's embedding vect…
Acoustic Modeling for End-to-End Empathetic Dialogue Speech Synthesis Using Linguistic and Prosodic Contexts of Dialogue History
Yuto Nishimura, Yuki Saito, Shinnosuke Takamichi +2
We propose an end-to-end empathetic dialogue speech synthesis (DSS) model that considers both the linguistic and prosodic contexts of dialogue history. Empathy is the active attemp…
STUDIES: Corpus of Japanese Empathetic Dialogue Speech Towards Friendly Voice Agent
Yuki Saito, Yuto Nishimura, Shinnosuke Takamichi +2
We present STUDIES, a new speech corpus for developing a voice agent that can speak in a friendly manner. Humans naturally control their speech prosody to empathize with each other…
HumanACGAN: conditional generative adversarial network with human-based auxiliary classifier and its evaluation in phoneme perception
Yota Ueda, Kazuki Fujii, Yuki Saito +3
We propose a conditional generative adversarial network (GAN) incorporating humans' perceptual evaluations. A deep neural network (DNN)-based generator of a GAN can represent a rea…
Lifter Training and Sub-band Modeling for Computationally Efficient and High-Quality Voice Conversion Using Spectral Differentials
Takaaki Saeki, Yuki Saito, Shinnosuke Takamichi +1
In this paper, we propose computationally efficient and high-quality methods for statistical voice conversion (VC) with direct waveform modification based on spectral differentials…
HumanGAN: generative adversarial network with human-based discriminator and its evaluation in speech perception modeling
Kazuki Fujii, Yuki Saito, Shinnosuke Takamichi +2
We propose the HumanGAN, a generative adversarial network (GAN) incorporating human perception as a discriminator. A basic GAN trains a generator to represent a real-data distribut…
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…
V2S attack: building DNN-based voice conversion from automatic speaker verification
Taiki Nakamura, Yuki Saito, Shinnosuke Takamichi +2
This paper presents a new voice impersonation attack using voice conversion (VC). Enrolling personal voices for automatic speaker verification (ASV) offers natural and flexible bio…
DNN-based Speaker Embedding Using Subjective Inter-speaker Similarity for Multi-speaker Modeling in Speech Synthesis
Yuki Saito, Shinnosuke Takamichi, Hiroshi Saruwatari
This paper proposes novel algorithms for speaker embedding using subjective inter-speaker similarity based on deep neural networks (DNNs). Although conventional DNN-based speaker e…
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…
Phase reconstruction from amplitude spectrograms based on von-Mises-distribution deep neural network
Shinnosuke Takamichi, Yuki Saito, Norihiro Takamune +2
This paper presents a deep neural network (DNN)-based phase reconstruction from amplitude spectrograms. In audio signal and speech processing, the amplitude spectrogram is often us…