10 papers
PASQA: Pitch-Accent-Focused Speech Quality Assessment Model Trained on Synthetic Speech with Accent Errors
Masaya Kawamura, Yuma Shirahata, Kentaro Mitsui +1
Existing mean opinion score (MOS) prediction models typically predict utterance-level naturalness MOS and can be insensitive to localized pitch-accent errors. We propose Pitch-Acce…
Investigating Human-Model Discrepancies in Speech Quality Assessment via Acoustic and Prosodic Perturbations
Masato Takagi, Masaya Kawamura, Reo Shimizu +1
Mean opinion score (MOS) prediction models are widely used as proxy metrics in text-to-speech (TTS) research, yet their ability to capture quality differences beyond acoustic fidel…
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…
Wave-Trainer-Fit: Neural Vocoder with Trainable Prior and Fixed-Point Iteration towards High-Quality Speech Generation from SSL features
Hien Ohnaka, Yuma Shirahata, Masaya Kawamura
We propose WaveTrainerFit, a neural vocoder that performs high-quality waveform generation from data-driven features such as SSL features. WaveTrainerFit builds upon the WaveFit vo…
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…
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…