35 citations · 44 across the 14 of their papers we have counts for
14 papers
Sarashina2.2-TTS: Tackling Kanji Polyphony in Japanese Speech Generation via Data Scaling and Targeted Data Synthesis
Lianbo Liu, Shiao Zhu, Kai Washizaki +10
While large language model (LLM)-based text-to-speech (TTS) systems have achieved high-quality speech synthesis, most existing systems focus on English and Chinese. Japanese, howev…
PSLM: Parallel Generation of Text and Speech with LLMs for Low-Latency Spoken Dialogue Systems
Kentaro Mitsui, Koh Mitsuda, Toshiaki Wakatsuki +2
Multimodal language models that process both text and speech have a potential for applications in spoken dialogue systems. However, current models face two major challenges in resp…
Release of Pre-Trained Models for the Japanese Language
Kei Sawada, Tianyu Zhao, Makoto Shing +5
AI democratization aims to create a world in which the average person can utilize AI techniques. To achieve this goal, numerous research institutes have attempted to make their res…
PeriodGrad: Towards Pitch-Controllable Neural Vocoder Based on a Diffusion Probabilistic Model
Yukiya Hono, Kei Hashimoto, Yoshihiko Nankaku +1
This paper presents a neural vocoder based on a denoising diffusion probabilistic model (DDPM) incorporating explicit periodic signals as auxiliary conditioning signals. Recently,…
Integrating Pre-Trained Speech and Language Models for End-to-End Speech Recognition
Yukiya Hono, Koh Mitsuda, Tianyu Zhao +3
Advances in machine learning have made it possible to perform various text and speech processing tasks, such as automatic speech recognition (ASR), in an end-to-end (E2E) manner. E…
Towards human-like spoken dialogue generation between AI agents from written dialogue
Kentaro Mitsui, Yukiya Hono, Kei Sawada
The advent of large language models (LLMs) has made it possible to generate natural written dialogues between two agents. However, generating human-like spoken dialogues from these…
Singing voice synthesis based on frame-level sequence-to-sequence models considering vocal timing deviation
Miku Nishihara, Yukiya Hono, Kei Hashimoto +2
This paper proposes singing voice synthesis (SVS) based on frame-level sequence-to-sequence models considering vocal timing deviation. In SVS, it is essential to synchronize the ti…
UniFLG: Unified Facial Landmark Generator from Text or Speech
Kentaro Mitsui, Yukiya Hono, Kei Sawada
Talking face generation has been extensively investigated owing to its wide applicability. The two primary frameworks used for talking face generation comprise a text-driven framew…
Singing Voice Synthesis Based on a Musical Note Position-Aware Attention Mechanism
Yukiya Hono, Kei Hashimoto, Yoshihiko Nankaku +1
This paper proposes a novel sequence-to-sequence (seq2seq) model with a musical note position-aware attention mechanism for singing voice synthesis (SVS). A seq2seq modeling approa…
Embedding a Differentiable Mel-cepstral Synthesis Filter to a Neural Speech Synthesis System
Takenori Yoshimura, Shinji Takaki, Kazuhiro Nakamura +5
This paper integrates a classic mel-cepstral synthesis filter into a modern neural speech synthesis system towards end-to-end controllable speech synthesis. Since the mel-cepstral…
End-to-End Text-to-Speech Based on Latent Representation of Speaking Styles Using Spontaneous Dialogue
Kentaro Mitsui, Tianyu Zhao, Kei Sawada +3
The recent text-to-speech (TTS) has achieved quality comparable to that of humans; however, its application in spoken dialogue has not been widely studied. This study aims to reali…
Sinsy: A Deep Neural Network-Based Singing Voice Synthesis System
Yukiya Hono, Kei Hashimoto, Keiichiro Oura +2
This paper presents Sinsy, a deep neural network (DNN)-based singing voice synthesis (SVS) system. In recent years, DNNs have been utilized in statistical parametric SVS systems, a…
PeriodNet: A non-autoregressive waveform generation model with a structure separating periodic and aperiodic components
Yukiya Hono, Shinji Takaki, Kei Hashimoto +3
We propose PeriodNet, a non-autoregressive (non-AR) waveform generation model with a new model structure for modeling periodic and aperiodic components in speech waveforms. The non…
Hierarchical Multi-Grained Generative Model for Expressive Speech Synthesis
Yukiya Hono, Kazuna Tsuboi, Kei Sawada +4
This paper proposes a hierarchical generative model with a multi-grained latent variable to synthesize expressive speech. In recent years, fine-grained latent variables are introdu…