English
Related papers

Related papers: High-quality Speech Synthesis Using Super-resoluti…

200 papers

Speech super-resolution (SR) is a task to increase speech sampling rate by generating high-frequency components. Existing speech SR methods are trained in constrained experimental settings, such as a fixed upsampling ratio. These strong…

Audio and Speech Processing · Electrical Eng. & Systems 2023-10-10 Haohe Liu , Woosung Choi , Xubo Liu , Qiuqiang Kong , Qiao Tian , DeLiang Wang

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 a enhancement…

Audio and Speech Processing · Electrical Eng. & Systems 2024-11-20 Hui-Peng Du , Ye-Xin Lu , Yang Ai , Zhen-Hua Ling

Previous works (Donahue et al., 2018a; Engel et al., 2019a) have found that generating coherent raw audio waveforms with GANs is challenging. In this paper, we show that it is possible to train GANs reliably to generate high quality…

Audio and Speech Processing · Electrical Eng. & Systems 2019-12-10 Kundan Kumar , Rithesh Kumar , Thibault de Boissiere , Lucas Gestin , Wei Zhen Teoh , Jose Sotelo , Alexandre de Brebisson , Yoshua Bengio , Aaron Courville

Speech Emotion Recognition (SER) affective technology enables the intelligent embedded devices to interact with sensitivity. Similarly, call centre employees recognise customers' emotions from their pitch, energy, and tone of voice so as to…

Sound · Computer Science 2023-12-19 David Hason Rudd , Huan Huo , Guandong Xu

Fine-grained editing of speech attributes$\unicode{x2014}$such as prosody (i.e., the pitch, loudness, and phoneme durations), pronunciation, speaker identity, and formants$\unicode{x2014}$is useful for fine-tuning and fixing imperfections…

Audio and Speech Processing · Electrical Eng. & Systems 2024-07-09 Max Morrison , Cameron Churchwell , Nathan Pruyne , Bryan Pardo

Recent advancement in Generative Adversarial Networks in speech synthesis domain[3],[2] have shown, that it's possible to train GANs [8] in a reliable manner for high quality coherent waveform generation from mel-spectograms. We propose…

Audio and Speech Processing · Electrical Eng. & Systems 2020-06-16 Luka Chkhetiani , Levan Bejanidze

Automatic methods to predict Mean Opinion Score (MOS) of listeners have been researched to assure the quality of Text-to-Speech systems. Many previous studies focus on architectural advances (e.g. MBNet, LDNet, etc.) to capture relations…

Sound · Computer Science 2022-06-29 Aki Kunikoshi , Jaebok Kim , Wonsuk Jun , Kåre Sjölander

While neural vocoders have made significant progress in high-fidelity speech synthesis, their application on polyphonic music has remained underexplored. In this work, we propose DisCoder, a neural vocoder that leverages a generative…

Recent speech language models rely on encoders that are optimized separately from autoregressive models. Since these encoders are unaware of the downstream objectives, the extracted representations may not be optimal for downstream tasks.…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-29 Sung-Lin Yeh , Wei Zhou , Gil Keren , Duc Le , Zhong Meng , Hao Tang , Jay Mahadeokar , Ozlem Kalinli , Alexandre Mourachko

Although diffusion models in text-to-speech have become a popular choice due to their strong generative ability, the intrinsic complexity of sampling from diffusion models harms their efficiency. Alternatively, we propose VoiceFlow, an…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-04 Yiwei Guo , Chenpeng Du , Ziyang Ma , Xie Chen , Kai Yu

Most deep learning-based models for speech enhancement have mainly focused on estimating the magnitude of spectrogram while reusing the phase from noisy speech for reconstruction. This is due to the difficulty of estimating the phase of…

Sound · Computer Science 2019-04-03 Hyeong-Seok Choi , Jang-Hyun Kim , Jaesung Huh , Adrian Kim , Jung-Woo Ha , Kyogu Lee

We describe a neural network-based system for text-to-speech (TTS) synthesis that is able to generate speech audio in the voice of many different speakers, including those unseen during training. Our system consists of three independently…

Computation and Language · Computer Science 2019-01-04 Ye Jia , Yu Zhang , Ron J. Weiss , Quan Wang , Jonathan Shen , Fei Ren , Zhifeng Chen , Patrick Nguyen , Ruoming Pang , Ignacio Lopez Moreno , Yonghui Wu

Designing a speech quality assessment (SQA) system for estimating mean-opinion-score (MOS) of multi-rate speech with varying sampling frequency (16-48 kHz) is a challenging task. The challenge arises due to the limited availability of a…

Audio and Speech Processing · Electrical Eng. & Systems 2026-02-17 Fengyuan Cao , Xinyu Liang , Fredrik Cumlin , Victor Ungureanu , Chandan K. A. Reddy , Christian Schuldt , Saikat Chatterjee

Historically, most speech models in machine-learning have used the mel-spectrogram as a speech representation. Recently, discrete audio tokens produced by neural audio codecs have become a popular alternate speech representation for speech…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-05 Ryan Langman , Ante Jukić , Kunal Dhawan , Nithin Rao Koluguri , Jason Li

For training the sequence-to-sequence voice conversion model, we need to handle an issue of insufficient data about the number of speech pairs which consist of the same utterance. This study experimentally investigated the effects of…

Machine Learning · Computer Science 2020-06-16 Yeongtae Hwang , Hyemin Cho , Hongsun Yang , Dong-Ok Won , Insoo Oh , Seong-Whan Lee

We describe speaker-independent speech synthesis driven by a small set of phonetically meaningful speech parameters such as formant frequencies. The intention is to leverage deep-learning advances to provide a highly realistic signal…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-06 Pablo Pérez Zarazaga , Zofia Malisz , Gustav Eje Henter , Lauri Juvela

Neural network-based Text-to-Speech has significantly improved the quality of synthesized speech. Prominent methods (e.g., Tacotron2, FastSpeech, FastPitch) usually generate Mel-spectrogram from text and then synthesize speech using vocoder…

Sound · Computer Science 2022-08-16 Mohammed Salah Al-Radhi , Tamás Gábor Csapó , Csaba Zainkó , Géza Németh

In recent years, the joint training of speech enhancement front-end and automatic speech recognition (ASR) back-end has been widely used to improve the robustness of ASR systems. Traditional joint training methods only use enhanced speech…

Sound · Computer Science 2023-05-31 Haoyu Lu , Nan Li , Tongtong Song , Longbiao Wang , Jianwu Dang , Xiaobao Wang , Shiliang Zhang

In this paper, we propose multi-band MelGAN, a much faster waveform generation model targeting to high-quality text-to-speech. Specifically, we improve the original MelGAN by the following aspects. First, we increase the receptive field of…

Sound · Computer Science 2020-11-18 Geng Yang , Shan Yang , Kai Liu , Peng Fang , Wei Chen , Lei Xie

Recent developments in speech synthesis have produced systems capable of outcome intelligible speech, but now researchers strive to create models that more accurately mimic human voices. One such development is the incorporation of multiple…

Sound · Computer Science 2016-02-09 Marvin Coto-Jiménez , John Goddard-Close