English
Related papers

Related papers: Eigenresiduals for improved Parametric Speech Synt…

200 papers

The evaluation of audio fingerprinting at a realistic scale is limited by the scarcity of large public music databases. We present an audio-free approach that synthesises latent fingerprints which approximate the distribution of real…

Sound · Computer Science 2025-09-24 Aditya Bhattacharjee , Marco Pasini , Emmanouil Benetos

We propose a method for generating low-frequency compensated synthetic impulse responses that improve the performance of far-field speech recognition systems trained on artificially augmented datasets. We design linear-phase filters that…

Sound · Computer Science 2021-09-28 Zhenyu Tang , Hsien-Yu Meng , Dinesh Manocha

Generative Models for Audio Synthesis have been gaining momentum in the last few years. More recently, parametric representations of the audio signal have been incorporated to facilitate better musical control of the synthesized output. In…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-20 Krishna Subramani , Preeti Rao

While automatic subjective speech quality assessment has witnessed much progress, an open question is whether an automatic quality assessment at frame resolution is possible. This would be highly desirable, as it adds explainability to the…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-10 Michael Kuhlmann , Fritz Seebauer , Petra Wagner , Reinhold Haeb-Umbach

In this paper, we aim at improving the performance of synthesized speech in statistical parametric speech synthesis (SPSS) based on a generative adversarial network (GAN). In particular, we propose a novel architecture combining the…

Sound · Computer Science 2017-07-12 Shan Yang , Lei Xie , Xiao Chen , Xiaoyan Lou , Xuan Zhu , Dongyan Huang , Haizhou Li

This paper introduces a novel method to separate noisy speech into low or high frequency frames, in order to improve fundamental frequency (F0) estimation accuracy. In this proposal, the target signal is analyzed by means of the ensemble…

Audio and Speech Processing · Electrical Eng. & Systems 2021-12-21 A. Queiroz , R. Coelho

Recent advances in neural autoregressive models have improve the performance of speech synthesis (SS). However, as they lack the ability to model global characteristics of speech (such as speaker individualities or speaking styles),…

Computation and Language · Computer Science 2019-02-12 Kei Akuzawa , Yusuke Iwasawa , Yutaka Matsuo

Advancements in deep neural networks have allowed automatic speech recognition (ASR) systems to attain human parity on several publicly available clean speech datasets. However, even state-of-the-art ASR systems experience performance…

Computation and Language · Computer Science 2023-10-17 Chen Chen , Yuchen Hu , Chao-Han Huck Yang , Sabato Macro Siniscalchi , Pin-Yu Chen , Eng Siong Chng

In this study, we present an approach to train a single speech enhancement network that can perform both personalized and non-personalized speech enhancement. This is achieved by incorporating a frame-wise conditioning input that specifies…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-24 Zhepei Wang , Ritwik Giri , Devansh Shah , Jean-Marc Valin , Michael M. Goodwin , Paris Smaragdis

This paper proposes a speech enhancement method which exploits the high potential of residual connections in a Wide Residual Network architecture. This is supported on single dimensional convolutions computed alongside the time domain,…

Audio and Speech Processing · Electrical Eng. & Systems 2019-04-11 Jorge Llombart , Dayana Ribas , Antonio Miguel , Luis Vicente , Alfonso Ortega , Eduardo Lleida

Customizing voice and speaking style in a speech synthesis system with intuitive and fine-grained controls is challenging, given that little data with appropriate labels is available. Furthermore, editing an existing human's voice also…

Sound · Computer Science 2023-10-27 Florian Lux , Pascal Tilli , Sarina Meyer , Ngoc Thang Vu

By representing speaker characteristic as a single fixed-length vector extracted solely from speech, we can train a neural multi-speaker speech synthesis model by conditioning the model on those vectors. This model can also be adapted to…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-09 Hieu-Thi Luong , Junichi Yamagishi

This paper proposes a deep denoising auto-encoder technique to extract better acoustic features for speech synthesis. The technique allows us to automatically extract low-dimensional features from high dimensional spectral features in a…

Sound · Computer Science 2015-06-18 Zhenzhou Wu , Shinji Takaki , Junichi Yamagishi

Whispered speech is produced when the vocal folds are not used, either intentionally, or due to a temporary or permanent voice condition. The essential difference between natural speech and whispered speech is that periodic signal…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-10 Aníbal J. S. Ferreira , Luis M. T. Jesus , Laurentino M. M. Leal , Jorge E. F. Spratley

Cross-speaker emotion transfer speech synthesis aims to synthesize emotional speech for a target speaker by transferring the emotion from reference speech recorded by another (source) speaker. In this task, extracting speaker-independent…

Sound · Computer Science 2022-07-05 Tao Li , Xinsheng Wang , Qicong Xie , Zhichao Wang , Mingqi Jiang , Lei Xie

Suffering from limited singing voice corpus, existing singing voice synthesis (SVS) methods that build encoder-decoder neural networks to directly generate spectrogram could lead to out-of-tune issues during the inference phase. To…

Sound · Computer Science 2021-10-13 Shujun Liu , Hai Zhu , Kun Wang , Huajun Wang

This paper introduces a novel data-driven strategy for synthesizing gramophone noise audio textures. A diffusion probabilistic model is applied to generate highly realistic quasiperiodic noises. The proposed model is designed to generate…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-01 Eloi Moliner , Vesa Välimäki

We propose a novel high-fidelity expressive speech synthesis model, UniTTS, that learns and controls overlapping style attributes avoiding interference. UniTTS represents multiple style attributes in a single unified embedding space by the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-02 Minsu Kang , Sungjae Kim , Injung Kim

Recently, deep learning-based generative models have been introduced to generate singing voices. One approach is to predict the parametric vocoder features consisting of explicit speech parameters. This approach has the advantage that the…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-14 Tae-Woo Kim , Min-Su Kang , Gyeong-Hoon Lee

A speech enhancement method based on probabilistic geometric approach to spectral subtraction (PGA) performed on short time magnitude spectrum is presented in this paper. A confidence parameter of noise estimation is introduced in the gain…

Audio and Speech Processing · Electrical Eng. & Systems 2018-02-15 Md Tauhidul Islam , Celia Shahnaz , Wei-Ping Zhu , M. Omair Ahmad
‹ Prev 1 3 4 5 6 7 10 Next ›