Search Results for author:
Found 14 papers, 4 papers with code
Description-based Controllable Text-to-Speech with Cross-Lingual Voice Control
We propose a novel description-based controllable text-to-speech (TTS) method with cross-lingual control capability.
LibriTTS-P: A Corpus with Speaking Style and Speaker Identity Prompts for Text-to-Speech and Style Captioning
We employ a hybrid approach to construct prompt annotations: (1) manual annotations that capture human perceptions of speaker characteristics and (2) synthetic annotations on speaking style.
Audio-conditioned phonemic and prosodic annotation for building text-to-speech models from unlabeled speech data
For creating a TTS dataset that consists of label-speech paired data, the proposed annotation model leverages an automatic speech recognition (ASR) model to obtain phonemic and prosodic labels from unlabeled speech samples.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
PromptTTS++: Controlling Speaker Identity in Prompt-Based Text-to-Speech Using Natural Language Descriptions
We propose PromptTTS++, a prompt-based text-to-speech (TTS) synthesis system that allows control over speaker identity using natural language descriptions.
CALLS: Japanese Empathetic Dialogue Speech Corpus of Complaint Handling and Attentive Listening in Customer Center
We present CALLS, a Japanese speech corpus that considers phone calls in a customer center as a new domain of empathetic spoken dialogue.
ChatGPT-EDSS: Empathetic Dialogue Speech Synthesis Trained from ChatGPT-derived Context Word Embeddings
We focus on ChatGPT's reading comprehension and introduce it to EDSS, a task of synthesizing speech that can empathize with the interlocutor's emotion.
Nonparallel High-Quality Audio Super Resolution with Domain Adaptation and Resampling CycleGANs
Neural audio super-resolution models are typically trained on low- and high-resolution audio signal pairs.
Period VITS: Variational Inference with Explicit Pitch Modeling for End-to-end Emotional Speech Synthesis
From these features, the proposed periodicity generator produces a sample-level sinusoidal source that enables the waveform decoder to accurately reproduce the pitch.
Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transform
We propose a lightweight end-to-end text-to-speech model using multi-band generation and inverse short-time Fourier transform.
Acoustic Modeling for End-to-End Empathetic Dialogue Speech Synthesis Using Linguistic and Prosodic Contexts of Dialogue History
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.
Cross-Speaker Emotion Transfer for Low-Resource Text-to-Speech Using Non-Parallel Voice Conversion with Pitch-Shift Data Augmentation
Because pitch-shift data augmentation enables the coverage of a variety of pitch dynamics, it greatly stabilizes training for both VC and TTS models, even when only 1, 000 utterances of the target speaker's neutral data are available.
STUDIES: Corpus of Japanese Empathetic Dialogue Speech Towards Friendly Voice Agent
We describe our methodology to construct an empathetic dialogue speech corpus and report the analysis results of the STUDIES corpus.
Phrase break prediction with bidirectional encoder representations in Japanese text-to-speech synthesis
We propose a novel phrase break prediction method that combines implicit features extracted from a pre-trained large language model, a. k. a BERT, and explicit features extracted from BiLSTM with linguistic features.
Full-body High-resolution Anime Generation with Progressive Structure-conditional Generative Adversarial Networks
Our method tackles the limitations by progressively increasing the resolution of both generated images and structural conditions during training.
