English
Related papers

Related papers: Statistical Parametric Speech Synthesis Using Bott…

200 papers

Neural audio codecs are at the core of modern conversational speech technologies, converting continuous speech into sequences of discrete tokens that can be processed by LLMs. However, existing codecs typically operate at fixed frame rates,…

Machine Learning · Computer Science 2026-02-05 Luca Della Libera , Cem Subakan , Mirco Ravanelli

We propose UnitSpeech, a speaker-adaptive speech synthesis method that fine-tunes a diffusion-based text-to-speech (TTS) model using minimal untranscribed data. To achieve this, we use the self-supervised unit representation as a pseudo…

Sound · Computer Science 2023-06-29 Heeseung Kim , Sungwon Kim , Jiheum Yeom , Sungroh Yoon

For our submission to the ZeroSpeech 2019 challenge, we apply discrete latent-variable neural networks to unlabelled speech and use the discovered units for speech synthesis. Unsupervised discrete subword modelling could be useful for…

Speech representation learning has improved both speech understanding and speech synthesis tasks for single language. However, its ability in cross-lingual scenarios has not been explored. In this paper, we extend the pretraining method for…

Audio and Speech Processing · Electrical Eng. & Systems 2022-12-06 Xiaoran Fan , Chao Pang , Tian Yuan , He Bai , Renjie Zheng , Pengfei Zhu , Shuohuan Wang , Junkun Chen , Zeyu Chen , Liang Huang , Yu Sun , Hua Wu

State of the art speech recognition systems use data-intensive context-dependent phonemes as acoustic units. However, these approaches do not translate well to low resourced languages where large amounts of training data is not available.…

Computation and Language · Computer Science 2016-06-21 Amir Hossein Harati Nejad Torbati , Joseph Picone

We propose a novel approach for few-shot talking-head synthesis. While recent works in neural talking heads have produced promising results, they can still produce images that do not preserve the identity of the subject in source images. We…

Computer Vision and Pattern Recognition · Computer Science 2021-04-30 Moustafa Meshry , Saksham Suri , Larry S. Davis , Abhinav Shrivastava

Many speech applications require understanding aspects beyond the words being spoken, such as recognizing emotion, detecting whether the speaker is wearing a mask, or distinguishing real from synthetic speech. In this work, we introduce a…

Sound · Computer Science 2022-12-14 Joel Shor , Aren Jansen , Wei Han , Daniel Park , Yu Zhang

Recent studies have introduced end-to-end TTS, which integrates the production of context and acoustic features in statistical parametric speech synthesis. As a result, a single neural network replaced laborious feature engineering with…

Machine Learning · Computer Science 2019-02-26 Kohki Mametani , Tsuneo Kato , Seiichi Yamamoto

Recent character and phoneme-based parametric TTS systems using deep learning have shown strong performance in natural speech generation. However, the choice between character or phoneme input can create serious limitations for practical…

Machine Learning · Computer Science 2018-11-27 Kyle Kastner , João Felipe Santos , Yoshua Bengio , Aaron Courville

The front-end module in multi-channel automatic speech recognition (ASR) systems mainly use microphone array techniques to produce enhanced signals in noisy conditions with reverberation and echos. Recently, neural network (NN) based…

Sound · Computer Science 2020-11-19 Yuxiang Kong , Jian Wu , Quandong Wang , Peng Gao , Weiji Zhuang , Yujun Wang , Lei Xie

This paper proposes novel algorithms for speaker embedding using subjective inter-speaker similarity based on deep neural networks (DNNs). Although conventional DNN-based speaker embedding such as a $d$-vector can be applied to…

Audio and Speech Processing · Electrical Eng. & Systems 2019-07-22 Yuki Saito , Shinnosuke Takamichi , Hiroshi Saruwatari

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

Synthesizing realistic co-speech gestures is an important and yet unsolved problem for creating believable motions that can drive a humanoid robot to interact and communicate with human users. Such capability will improve the impressions of…

Computer Vision and Pattern Recognition · Computer Science 2023-03-24 Shuhong Lu , Youngwoo Yoon , Andrew Feng

Statistical parametric speech synthesizers have recently shown their ability to produce natural-sounding and flexible voices. Unfortunately the delivered quality suffers from a typical buzziness due to the fact that speech is vocoded. This…

Sound · Computer Science 2020-01-06 Thomas Drugman , Geoffrey Wilfart , Thierry Dutoit

This paper introduces a deep neural network model for subband-based speech synthesizer. The model benefits from the short bandwidth of the subband signals to reduce the complexity of the time-domain speech generator. We employed the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-28 Azam Rabiee , Geonmin Kim , Tae-Ho Kim , Soo-Young Lee

Deep metric learning aims to learn embeddings that contain semantic similarity information among data points. To learn better embeddings, methods to generate synthetic hard samples have been proposed. Existing methods of synthetic hard…

Computer Vision and Pattern Recognition · Computer Science 2020-04-24 Geonmo Gu , Byungsoo Ko

Speech Neuroprostheses have the potential to enable communication for people with dysarthria or anarthria. Recent advances have demonstrated high-quality text decoding and speech synthesis from electrocorticographic grids placed on the…

This paper presents a statistical method of single-channel speech enhancement that uses a variational autoencoder (VAE) as a prior distribution on clean speech. A standard approach to speech enhancement is to train a deep neural network…

We present a method for blind acoustic parameter estimation from single-channel reverberant speech. The method is structured into three stages. In the first stage, a variational auto-encoder is trained to extract latent representations of…

Audio and Speech Processing · Electrical Eng. & Systems 2024-07-30 Philipp Götz , Cagdas Tuna , Andreas Brendel , Andreas Walther , Emanuël A. P. Habets

Time-frequency masking or spectrum prediction computed via short symmetric windows are commonly used in low-latency deep neural network (DNN) based source separation. In this paper, we propose the usage of an asymmetric analysis-synthesis…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-23 Shanshan Wang , Gaurav Naithani , Archontis Politis , Tuomas Virtanen