paper-with-me

Papers

Stochastic Pitch Prediction Improves the Diversity and Naturalness of Speech in Glow-TTS

2023-05-28 · Sewade Ogun, Vincent Colotte, Emmanuel Vincent

Flow-based generative models are widely used in text-to-speech (TTS) systems to learn the distribution of audio features (e.g., Mel-spectrograms) given the input tokens and to sample from this distribution to generate diverse utterances. However, in the zero-shot multi-speaker TTS scenario, the generated utterances lack diversity and naturalness. In this paper, we propose to improve the diversity of utterances by explicitly learning the distribution of fundamental frequency sequences (pitch contours) of each speaker during training using a stochastic flow-based pitch predictor, then conditioning the model on generated pitch contours during inference. The experimental results demonstrate that the proposed method yields a significant improvement in the naturalness and diversity of speech generated by a Glow-TTS model that uses explicit stochastic pitch prediction, over a Glow-TTS baseline and an improved Glow-TTS model that uses a stochastic duration predictor.

📄 PDF Abstract BibTeX arXiv:2305.17724

Code (1)

ogunlao/glowtts_stdp 공식 구현 pytorch

Tasks

Diversitytext-to-speechText to SpeechZero-Shot Multi-Speaker TTS

Methods 이 논문이 사용한 방법론

Activation Normalization Activation Normalization is a type of normalization used for flow-based generative models; specifically it was introduced in the GLOW
Invertible 1x1 Convolution The Invertible 1x1 Convolution is a type of convolution used in flow-based generative models that reverses the ordering of…
Affine Coupling 설명 없음
Normalizing Flows Normalizing Flows are a method for constructing complex distributions by transforming a probability density through a series of invertible mappings. By repeatedly applying…
GLOW 설명 없음
Glow-TTS Glow-TTS is a flow-based generative model for parallel TTS that does not require any external aligner. By combining the properties of flows and dynamic programming, the…

Similar Papers 제목 키워드 기반

BERT-APC: A Reference-free Framework for Automatic Pitch Correction via Musical Context Inference

2025-11-25 · Sungjae Kim, Kihyun Na, Jinyoung Choi, Injung Kim arxiv

Automatic Pitch Correction (APC) enhances vocal recordings by aligning pitch deviations with intended musical notes. However, existing APC systems either rely on reference pitches, which limits practical applicability, o…

Data Augmentation

Period VITS: Variational Inference with Explicit Pitch Modeling for End-to-end Emotional Speech Synthesis

2022-10-28 · Yuma Shirahata, Ryuichi Yamamoto, Eunwoo Song, Ryo Terashima 외

Several fully end-to-end text-to-speech (TTS) models have been proposed that have shown better performance compared to cascade models (i.e., training acoustic and vocoder models separately). However, they often generate …

DecoderDiversityEmotional Speech SynthesisSpeech Synthesis+3

Lightweight and perceptually-guided voice conversion for electro-laryngeal speech

2026-01-07 · Benedikt Mayrhofer, Franz Pernkopf, Philipp Aichinger, Martin Hagmüller arxiv

Electro-laryngeal (EL) speech is characterized by constant pitch, limited prosody, and mechanical noise, reducing naturalness and intelligibility. We propose a lightweight adaptation of the state-of-the-art StreamVC fram…

Voice Conversion

PASQA: Pitch-Accent-Focused Speech Quality Assessment Model Trained on Synthetic Speech with Accent Errors

2026-06-18 · Masaya Kawamura, Yuma Shirahata, Kentaro Mitsui, Reo Shimizu arxiv

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-Accent-focused Speech Quality Assessment (PA…

UtterTune: LoRA-Based Target-Language Pronunciation Edit and Control in Multilingual Text-to-Speech

2025-08-13 · Shuhei Kato arxiv

We propose UtterTune, a lightweight method for adapting a multilingual text-to-speech (TTS) system built on a large language model (LLM). It improves control of pronunciation in the target language while preserving perfo…