检索结果-内蒙古大学图书馆

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Caetano, Marcelo Rodet, Xavier Analysis/Synthesis Team IRCAM France

ISBN: (纸本)9781467300469

The model used to represent musical instrument sounds plays a crucial role in the quality of sound transformations. Ideally, the representation should be compact and accurate, while its parameters should give flexibility to independently manipulate perceptually related features of the sounds. This work describes a source-filter model for musical instrument sounds based on the sinusoidal plus residual decomposition. The sinusoidal component is modeled as sinusoidal partial tracks (source) and a time-varying spectral envelope (filter), and the residual is represented as white noise (source) shaped by a time-varying spectral envelope (filter). This article presents estimation and representation techniques that give totally independent and intuitive control of the spectral envelope model and the frequencies of the partials to perform perceptually related sound transformations. The result of a listening test confirmed that, in general, the sounds resynthesized from the source-filter model are perceptually similar to the original recordings.

关键词： source-filter model sinusoidal models musical instrument timbre sound transformations

来源：评论

学校读者我要写书评

暂无评论

A dual source-filter model of snore audio for snorer group classification 18

A dual source-filter model of snore audio for snorer group c...

引用

18th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2017)

作者： Rao, Achuth M., V Yadav, Shivani Ghosh, Prasanta Kumar Indian Inst Sci Elect Engn Bangalore 560012 Karnataka India Indian Inst Sci BioSyst Sci & Engn Bangalore 560012 Karnataka India

ISBN: (纸本)9781510848764

Snoring is a common symptom of serious chronic disease known as obstructive sleep apnea (OSA). Knowledge about the location of obstruction site (V- Velum, O- Oropharyngeal lateral walls, T-Tongue, E-Epiglottis) in the upper airways is necessary for proper surgical treatment. In this paper we propose a dual source-filter model similar to the source-filter model of speech to approximate the generation process of snore audio. The first filter models the vocal tract from lungs to the point of obstruction with white noise excitation from the lungs. The second filter models the vocal tract from the obstruction point to the lips/nose with impulse train excitation which represents vibrations at the point of obstruction. The filter coefficients are estimated using the closed and open phases of the snore beat cycle. VOTE classification is done by using SVM classifier and filter coefficients as features. The classification experiments are performed on the development set (283 snore audios) of the MUNICH-PASSAU SNORE SOUND CORPUS (MPSSC). We obtain an unweighted average recall (UAR) of 49.58%, which is higher than the INTERSPEECH-2017 snoring sub-challenge baseline technique by similar to 3% (absolute).

关键词： snore classification source-filter model sparsity

来源：评论

学校读者我要写书评

暂无评论

Robust Speech Analysis Based on source-filter model Using Multivariate Empirical Mode Decomposition in Noisy Environments 18th

Robust Speech Analysis Based on Source-Filter Model Using Mu...

引用

18th Speech and Computer International Conference (SPECOM)

作者： Boonkla, Surasak Unoki, Masashi Makhanov, Stanislav S. Japan Adv Inst Sci & Technol Sch Informat Sci Nomi Japan Thammasat Univ Sirindhorn Int Inst Technol Pathum Thani Thailand

ISBN: (纸本)9783319439587;9783319439570

This paper proposes a robust speech analysis method based on source-filter model using multivariate empirical mode decomposition (MEMD) under noisy conditions. The proposed method has two stages. At the first stage, magnitude spectrum of noisy speech signal is decomposed by MEMD into intrinsic mode functions (IMFs), and then IMFs corresponded to noise part are removed from them. At the second stage, log-magnitude spectrum of noise-reduced signals are decomposed into IMFs. Then, these are divided into two groups: the first group characterized by spectral fine structure for fundamental frequency estimation and the second group characterized by frequency response of vocal-tract filter for formant frequencies estimation. As opposed to the conventional linear prediction (LP) and cepstrum methods, the proposed method decomposes noise automatically in magnitude spectral domain and makes noise mixture become sparse in log-magnitude spectral domain. The results show that the proposed method outperforms LP and cepstrum methods under noisy conditions.

关键词： Multivariate empirical mode decomposition Speech analysis Fundamental frequency Formant frequency source-filter model

来源：评论

学校读者我要写书评

暂无评论

SFNet: A Computationally Efficient source filter model Based Neural Speech Synthesis

引用

IEEE SIGNAL PROCESSING LETTERS 2020年 27卷 1170-1174页

作者： Rao, Achuth M., V Ghosh, Prasanta Kumar Indian Inst Sci Dept Elect Engn Bangalore 560012 Karnataka India

Recently, neural speech synthesizers have achieved a high-quality synthesis for text-to-speech applications, but a real-time synthesis is possible only in the devices which have high memory and allow large computational complexity. In this work, we reduce the complexity of a speech synthesizer by reformulating the source-filter model of speech where the excitation signal is modeled as a sum of two signals. The first signal contains an impulse train that is computed from the pitch sequence. The second signal is modeled as white noise passed through a filter bank with frequency dependent gains. The parameters of the reformulated source-filter model are predicted using a neural network, referred to as SFNet. The network parameters are learnt by training the network using l(1)-error between the log Mel-spectrum of the predicted waveform and that of the ground-truth waveform. We demonstrate that there is a significant reduction in the memory and computational complexity compared to the state-of-the-art speaker independent neural speech synthesizer without any loss of the naturalness of the synthesized speech.

关键词： Neural vocoder source-filter model computational complexity Mel-spectrum

来源：评论

学校读者我要写书评

暂无评论

Using Cyclic Noise as the source Signal for Neural source-filter-based Speech Waveform model 21

Using Cyclic Noise as the Source Signal for Neural Source-Fi...

引用

Interspeech Conference

作者： Wang, Xin Yamagishi, Junichi Natl Inst Informat Tokyo Japan Univ Edinburgh CSTR Edinburgh Midlothian Scotland

ISBN: (纸本)9781713820697

Neural source-filter (NSF) waveform models generate speech waveforms by morphing sine-based source signals through dilated convolution in the time domain. Although the sine-based source signals help the NSF models to produce voiced sounds with specified pitch, the sine shape may constrain the generated waveform when the target voiced sounds are less periodic. In this paper, we propose a more flexible source signal called cyclic noise, a quasi-periodic noise sequence given by the convolution of a pulse train and a static random noise with a trainable decaying rate that controls the signal shape. We further propose a masked spectral loss to guide the NSF models to produce periodic voiced sounds from the cyclic noise-based source signal. Results from a large-scale listening test demonstrated the effectiveness of the cyclic noise and the masked spectral loss on speaker-independent NSF models in copy-synthesis experiments on the CMU ARCTIC database.

关键词： speech synthesis source-filter model harmonic-plus-noise waveform model neural network

来源：评论

学校读者我要写书评

暂无评论

Vibrato in singing source-filter and voice: The link between sinusoidal models

引用

EURASIP JOURNAL ON APPLIED SIGNAL PROCESSING 2004年第7期2004卷 1007-1020页

作者： Arroabarren, I Carlosena, A Univ Publ Navarra Dept Ingn Elect & Elect Pamplona 31006 Spain

The application of inverse filtering techniques for high-quality singing voice analysis/synthesis is discussed. In the context of source-filter models, inverse filtering provides a noninvasive method to extract the voice source, and thus to study voice quality. Although this approach is widely used in speech synthesis, this is not the case in singing voice. Several studies have proved that inverse filtering techniques fail in the case of singing voice, the reasons being unclear. In order to shed light on this problem, we will consider here an additional feature of singing voice, not present in speech: the vibrato. Vibrato has been traditionally studied by sinusoidal modeling. As an alternative, we will introduce here a novel noninteractive source filter model that incorporates the mechanisms of vibrato generation. This model will also allow the comparison of the results produced by inverse filtering techniques and by sinusoidal modeling, as they apply to singing voice and not to speech. In this way, the limitations of these conventional techniques, described in previous literature, will be explained. Both synthetic signals and singer recordings are used to validate and compare the techniques presented in the paper.

关键词： voice quality source-filter model inverse filtering singing voice vibrato sinusoidal model

来源：评论

学校读者我要写书评

暂无评论

Learning and controlling the source-filter representation of speech with a variational autoencoder

引用

SPEECH COMMUNICATION 2023年 148卷 53-65页

作者： Sadok, Samir Leglaive, Simon Girin, Laurent Alameda-Pineda, Xavier Seguier, Renaud CNRS CentraleSupelec IETR UMR 6164 Paris France Univ Grenoble Alpes GIPSA Lab CNRS Grenoble INP Grenoble France Univ Grenoble Alpes Inria CNRS LJK Grenoble France

Understanding and controlling latent representations in deep generative models is a challenging yet important problem for analyzing, transforming and generating various types of data. In speech processing, inspiring from the anatomical mechanisms of phonation, the source-filter model considers that speech signals are produced from a few independent and physically meaningful continuous latent factors, among which the fundamental frequency f(0) and the formants are of primary importance. In this work, we start from a variational autoencoder (VAE) trained in an unsupervised manner on a large dataset of unlabeled natural speech signals, and we show that the source-filter model of speech production naturally arises as orthogonal subspaces of the VAE latent space. Using only a few seconds of labeled speech signals generated with an artificial speech synthesizer, we propose a method to identify the latent subspaces encoding f(0) and the first three formant frequencies, we show that these subspaces are orthogonal, and based on this orthogonality, we develop a method to accurately and independently control the source-filter speech factors within the latent subspaces. Without requiring additional information such as text or human-labeled data, this results in a deep generative model of speech spectrograms that is conditioned on f(0) and the formant frequencies, and which is applied to the transformation speech signals. Finally, we also propose a robust f(0) estimation method that exploits the projection of a speech signal onto the learned latent subspace associated with f(0).

关键词： Representation learning Deep generative models Variational autoencoder source-filter model

来源：评论

学校读者我要写书评

暂无评论

High-Fidelity and Pitch-Controllable Neural Vocoder Based on Unified source-filter Networks

引用

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 2023年 31卷 3717-3729页

作者： Yoneyama, Reo Wu, Yi-Chiao Toda, Tomoki Nagoya Univ Grad Sch Informat Nagoya 4648601 Japan Nagoya Univ Informat Technol Ctr Nagoya 4648601 Japan

We introduce unified source-filter generative adversarial networks (uSFGAN), a waveform generative model conditioned on acoustic features, which represents the source-filter architecture in a generator network. Unlike the previous neural-based source-filter models in which parametric signal process modules are combined with neural networks, our approach enables unified optimization of both the source excitation generation and resonance filtering parts to achieve higher sound quality. In the uSFGAN framework, several specific regularization losses are proposed to enable the source excitation generation part to output reasonable source excitation signals. Both objective and subjective experiments are conducted, and the results demonstrate that the proposed uSFGAN achieves comparable sound quality to HiFi-GAN in the speech reconstruction task and outperforms WORLD in the F-0 transformation task. Moreover, we argue that the F-0-driven mechanism and the inductive bias obtained by source-filter modeling improve the robustness against unseen F-0 in training as shown by the results of experimental evaluations. Audio samples are available at our demo site at https://***/PitchControllableNeuralVocoder-Demo/.

关键词： Vocoders Controllability Speech processing Neural networks Training Mathematical models Acoustics Speech synthesis neural vocoder source-filter model unified source-filter networks

来源：评论

学校读者我要写书评

暂无评论

source-filter-Based Generative Adversarial Neural Vocoder for High Fidelity Speech Synthesis 1

引用

17th National Conference on Man-Machine Speech Communication

作者： Lu, Ye-Xin Ai, Yang Ling, Zhen-Hua Univ Sci & Technol China Natl Engn Res Ctr Speech & Language Informat Proc Hefei Peoples R China

ISBN: (数字)9789819924011

ISBN: (纸本)9789819924004;9789819924011

This paper proposes a source-filter-based generative adversarial neural vocoder named SF-GAN, which achieves high-fidelity waveform generation from input acoustic features by introducing F0-based source excitation signals to a neural filter framework. The SF-GAN vocoder is composed of a source module and a resolution-wise conditional filter module and is trained based on generative adversarial strategies. The source module produces an excitation signal from the F0 information, then the resolution-wise convolutional filter module combines the excitation signal with processed acoustic features at various temporal resolutions and finally reconstructs the raw waveform. The experimental results show that our proposed SF-GAN vocoder outperforms the state-of-the-art HiFi-GAN and Fre-GAN in both analysis-synthesis (AS) and text-to-speech (TTS) tasks, and the synthesized speech quality of SF-GAN is comparable to the ground-truth audio.

关键词： Neural vocoder source-filter model Generative adversarial networks Speech synthesis

来源：评论

学校读者我要写书评

暂无评论

Unified source-filter GAN with Harmonic-plus-Noise source Excitation Generation 23

Unified Source-Filter GAN with Harmonic-plus-Noise Source Ex...

引用

Interspeech Conference

作者： Yoneyama, Reo Wu, Yi-Chiao Toda, Tomoki Nagoya Univ Nagoya Aichi Japan

This paper introduces a unified source-filter network with a harmonic-plus-noise source excitation generation mechanism. In our previous work, we proposed unified source-filter GAN (uSFGAN) for developing a high-fidelity neural vocoder with flexible voice controllability using a unified source-filter neural network architecture. However, the capability of uSFGAN to model the aperiodic source excitation signal is insufficient, and there is still a gap in sound quality between the natural and generated speech. To improve the source excitation modeling and generated sound quality, a new source excitation generation network separately generating periodic and aperiodic components is proposed. The advanced adversarial training procedure of HiFiGAN is also adopted to replace that of Parallel WaveGAN used in the original uSFGAN. Both objective and subjective evaluation results show that the modified uSFGAN significantly improves the sound quality of the basic uSFGAN while maintaining the voice controllability.

关键词： Speech synthesis neural vocoder source-filter model generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：