5 papers
CC-G2PnP: Streaming Grapheme-to-Phoneme and prosody with Conformer-CTC for unsegmented languages
Yuma Shirahata, Ryuichi Yamamoto
We propose CC-G2PnP, a streaming grapheme-to-phoneme and prosody (G2PnP) model to connect large language model and text-to-speech in a streaming manner. CC-G2PnP is based on Confor…
Wavehax: Aliasing-Free Neural Waveform Synthesis Based on 2D Convolution and Harmonic Prior for Reliable Complex Spectrogram Estimation
Reo Yoneyama, Atsushi Miyashita, Ryuichi Yamamoto +1
Neural vocoders often struggle with aliasing in latent feature spaces, caused by time-domain nonlinear operations and resampling layers. Aliasing folds high-frequency components in…
Grapheme-Coherent Phonemic and Prosodic Annotation of Speech by Implicit and Explicit Grapheme Conditioning
Hien Ohnaka, Yuma Shirahata, Byeongseon Park +1
We propose a model to obtain phonemic and prosodic labels of speech that are coherent with graphemes. Unlike previous methods that simply fine-tune a pre-trained ASR model with the…
Comparative Analysis of Fast and High-Fidelity Neural Vocoders for Low-Latency Streaming Synthesis in Resource-Constrained Environments
Reo Yoneyama, Masaya Kawamura, Ryo Terashima +2
In real-time speech synthesis, neural vocoders often require low-latency synthesis through causal processing and streaming. However, streaming introduces inefficiencies absent in b…
BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing
Masaya Kawamura, Takuya Hasumi, Yuma Shirahata +1
This paper proposes a highly compact, lightweight text-to-speech (TTS) model for on-device applications. To reduce the model size, the proposed model introduces two techniques. Fir…