English
Related papers

Related papers: Effective Use of Variational Embedding Capacity in…

200 papers

We present an extension to the Tacotron speech synthesis architecture that learns a latent embedding space of prosody, derived from a reference acoustic representation containing the desired prosody. We show that conditioning Tacotron on…

Computation and Language · Computer Science 2018-03-28 RJ Skerry-Ryan , Eric Battenberg , Ying Xiao , Yuxuan Wang , Daisy Stanton , Joel Shor , Ron J. Weiss , Rob Clark , Rif A. Saurous

Modeling the rich prosodic variations inherent in human speech is essential for generating natural-sounding speech. While speaker embeddings are commonly used as conditioning inputs in personalized speech generation, they are typically…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-22 Ismail Rasim Ulgen , John H. L. Hansen , Carlos Busso , Berrak Sisman

This paper proposes an Expressive Speech Synthesis model that utilizes token-level latent prosodic variables in order to capture and control utterance-level attributes, such as character acting voice and speaking style. Current works aim to…

Speaker embeddings represent a means to extract representative vectorial representations from a speech signal such that the representation pertains to the speaker identity alone. The embeddings are commonly used to classify and discriminate…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-07 Adriana Stan

With the popularity of deep neural network, speech synthesis task has achieved significant improvements based on the end-to-end encoder-decoder framework in the recent days. More and more applications relying on speech synthesis technology…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-23 Dongyang Dai , Li Chen , Yuping Wang , Mu Wang , Rui Xia , Xuchen Song , Zhiyong Wu , Yuxuan Wang

Semantic sentence embedding models encode natural language sentences into vectors, such that closeness in embedding space indicates closeness in the semantics between the sentences. Bilingual data offers a useful signal for learning such…

Computation and Language · Computer Science 2020-11-20 John Wieting , Graham Neubig , Taylor Berg-Kirkpatrick

High-fidelity speech can be synthesized by end-to-end text-to-speech models in recent years. However, accessing and controlling speech attributes such as speaker identity, prosody, and emotion in a text-to-speech system remains a challenge.…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-05 Zexin Cai , Chuxiong Zhang , Ming Li

We propose prosody embeddings for emotional and expressive speech synthesis networks. The proposed methods introduce temporal structures in the embedding networks, thus enabling fine-grained control of the speaking style of the synthesized…

Computation and Language · Computer Science 2019-02-19 Younggun Lee , Taesu Kim

We propose a novel neural waveform compression method to catalyze emerging speech semantic communications. By introducing nonlinear transform and variational modeling, we effectively capture the dependencies within speech frames and…

Sound · Computer Science 2022-12-14 Shengshi Yao , Zixuan Xiao , Sixian Wang , Jincheng Dai , Kai Niu , Ping Zhang

Conventional word embeddings represent words with fixed vectors, which are usually trained based on co-occurrence patterns among words. In doing so, however, the power of such representations is limited, where the same word might be…

Computation and Language · Computer Science 2020-01-10 Hongming Zhang , Jiaxin Bai , Yan Song , Kun Xu , Changlong Yu , Yangqiu Song , Wilfred Ng , Dong Yu

In the existing cross-speaker style transfer task, a source speaker with multi-style recordings is necessary to provide the style for a target speaker. However, it is hard for one speaker to express all expected styles. In this paper, a…

Audio and Speech Processing · Electrical Eng. & Systems 2021-12-24 Qicong Xie , Tao Li , Xinsheng Wang , Zhichao Wang , Lei Xie , Guoqiao Yu , Guanglu Wan

The end-to-end speech synthesis model can directly take an utterance as reference audio, and generate speech from the text with prosody and speaker characteristics similar to the reference audio. However, an appropriate acoustic embedding…

Sound · Computer Science 2021-10-12 Cheng Gong , Longbiao Wang , Zhenhua Ling , Ju Zhang , Jianwu Dang

Text-to-speech systems recently achieved almost indistinguishable quality from human speech. However, the prosody of those systems is generally flatter than natural speech, producing samples with low expressiveness. Disentanglement of…

Variational autoencoder-based voice conversion (VAE-VC) has the advantage of requiring only pairs of speeches and speaker labels for training. Unlike the majority of the research in VAE-VC which focuses on utilizing auxiliary losses or…

Sound · Computer Science 2021-12-07 Kei Akuzawa , Kotaro Onishi , Keisuke Takiguchi , Kohki Mametani , Koichiro Mori

Textless speech-to-speech translation systems are rapidly advancing, thanks to the integration of self-supervised learning techniques. However, existing state-of-the-art systems fall short when it comes to capturing and transferring…

Sound · Computer Science 2023-10-12 Jarod Duret , Benjamin O'Brien , Yannick Estève , Titouan Parcollet

Spoken language understanding is typically based on pipeline architectures including speech recognition and natural language understanding steps. These components are optimized independently to allow usage of available data, but the overall…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-13 Pavel Denisov , Ngoc Thang Vu

Introducing variability while maintaining coherence is a core task in learning to generate utterances in conversation. Standard neural encoder-decoder models and their extensions using conditional variational autoencoder often result in…

Computation and Language · Computer Science 2018-10-23 Hung Le , Truyen Tran , Thin Nguyen , Svetha Venkatesh

In this paper, we introduce the Variational Autoencoder (VAE) to an end-to-end speech synthesis model, to learn the latent representation of speaking styles in an unsupervised manner. The style representation learned through VAE shows good…

Computation and Language · Computer Science 2019-02-15 Ya-Jie Zhang , Shifeng Pan , Lei He , Zhen-Hua Ling

End-to-end speech recognition is a promising technology for enabling compact automatic speech recognition (ASR) systems since it can unify the acoustic and language model into a single neural network. However, as a drawback, training of…

Computation and Language · Computer Science 2022-02-17 Yotaro Kubo , Shigeki Karita , Michiel Bacchiani

In this work, we extend ClariNet (Ping et al., 2019), a fully end-to-end speech synthesis model (i.e., text-to-wave), to generate high-fidelity speech from multiple speakers. To model the unique characteristic of different voices, low…

Computation and Language · Computer Science 2019-07-11 Jihyun Park , Kexin Zhao , Kainan Peng , Wei Ping
‹ Prev 1 2 3 10 Next ›