paper-with-me

Papers

Knowledge-and-Data-Driven Amplitude Spectrum Prediction for Hierarchical Neural Vocoders

2020-05-18

In our previous work, we have proposed a neural vocoder called HiNet which recovers speech waveforms by predicting amplitude and phase spectra hierarchically from input acoustic features. In HiNet, the amplitude spectrum predictor (ASP) predicts log amplitude spectra (LAS) from input acoustic features. This paper proposes a novel knowledge-and-data-driven ASP (KDD-ASP) to improve the conventional one. First, acoustic features (i.e., F0 and mel-cepstra) pass through a knowledge-driven LAS recovery module to obtain approximate LAS (ALAS). This module is designed based on the combination of STFT and source-filter theory, in which the source part and the filter part are designed based on input F0 and mel-cepstra, respectively. Then, the recovered ALAS are processed by a data-driven LAS refinement module which consists of multiple trainable convolutional layers to get the final LAS. Experimental results show that the HiNet vocoder using KDD-ASP can achieve higher quality of synthetic speech than that using conventional ASP and the WaveRNN vocoder on a text-to-speech (TTS) task.

📄 PDF Abstract BibTeX arXiv:2004.07832

Code (0)

등록된 구현이 없습니다.

Tasks

text-to-speechText to Speech

Similar Papers 제목 키워드 기반

Stage-Wise and Prior-Aware Neural Speech Phase Prediction

2024-10-07 · Fei Liu, Yang Ai, Hui-Peng Du, Ye-Xin Lu 외

This paper proposes a novel Stage-wise and Prior-aware Neural Speech Phase Prediction (SP-NSPP) model, which predicts the phase spectrum from input amplitude spectrum by two-stage neural networks. In the initial prior-co…

Prediction

Frequency Domain-Based Diffusion Model for Unpaired Image Dehazing

2025-07-02 · Chengxu Liu, Lu Qi, Jinshan Pan, Xueming Qian 외 arxiv

Unpaired image dehazing has attracted increasing attention due to its flexible data requirements during model training. Dominant methods based on contrastive learning not only introduce haze-unrelated content information…

Contrastive LearningImage Dehazing

A Neural Denoising Vocoder for Clean Waveform Generation from Noisy Mel-Spectrogram based on Amplitude and Phase Predictions

2024-11-19 · Hui-Peng Du, Ye-Xin Lu, Yang Ai, Zhen-Hua Ling

This paper proposes a novel neural denoising vocoder that can generate clean speech waveforms from noisy mel-spectrograms. The proposed neural denoising vocoder consists of two components, i.e., a spectrum predictor and …

DenoisingSpeech Enhancement

A New Statistic Feature of the Short-Time Amplitude Spectrum Values for Human's Unvoiced Pronunciation

2016-09-23 · Xiaodong Zhuang

In this paper, a new statistic feature of the discrete short-time amplitude spectrum is discovered by experiments for the signals of unvoiced pronunciation. For the random-varying short-time spectrum, this feature reveal…

Towards High-Quality and Efficient Speech Bandwidth Extension with Parallel Amplitude and Phase Prediction

2024-01-12 · Ye-Xin Lu, Yang Ai, Hui-Peng Du, Zhen-Hua Ling

Speech bandwidth extension (BWE) refers to widening the frequency bandwidth range of speech signals, enhancing the speech quality towards brighter and fuller. This paper proposes a generative adversarial network (GAN) ba…

Bandwidth ExtensionCPUGenerative Adversarial NetworkGPU