English
Related papers

Related papers: Knowing What to Stress: A Discourse-Conditioned Te…

200 papers

Although recent neural text-to-speech (TTS) systems have achieved high-quality speech synthesis, there are cases where a TTS system generates low-quality speech, mainly caused by limited training data or information loss during knowledge…

Audio and Speech Processing · Electrical Eng. & Systems 2022-05-26 Yeunju Choi , Youngmoon Jung , Youngjoo Suh , Hoirin Kim

While text-conditional 3D object generation and manipulation have seen rapid progress, the evaluation of coherence between generated 3D shapes and input textual descriptions lacks a clear benchmark. The reason is twofold: a) the low quality…

Computer Vision and Pattern Recognition · Computer Science 2023-09-15 Andrea Amaduzzi , Giuseppe Lisanti , Samuele Salti , Luigi Di Stefano

Modern neural text-to-speech (TTS) synthesis can generate speech that is indistinguishable from natural speech. However, the prosody of generated utterances often represents the average prosodic style of the database instead of having wide…

Audio and Speech Processing · Electrical Eng. & Systems 2020-09-16 Tuomo Raitio , Ramya Rasipuram , Dan Castellani

The potential of synthetic data in text-to-speech (TTS) model training has gained increasing attention, yet its rationality and effectiveness require systematic validation. In this study, we systematically investigate the feasibility of…

Sound · Computer Science 2025-12-22 Tingxiao Zhou , Leying Zhang , Zhengyang Chen , Yanmin Qian

Humans often speak in a continuous manner which leads to coherent and consistent prosody properties across neighboring utterances. However, most state-of-the-art speech synthesis systems only consider the information within each sentence…

Sound · Computer Science 2023-05-19 Ya-Jie Zhang , Wei Song , Yanghao Yue , Zhengchen Zhang , Youzheng Wu , Xiaodong He

The prosody of a spoken utterance, including features like stress, intonation and rhythm, can significantly affect the underlying semantics, and as a consequence can also affect its textual translation. Nevertheless, prosody is rarely…

Computation and Language · Computer Science 2024-11-01 Ioannis Tsiamas , Matthias Sperber , Andrew Finch , Sarthak Garg

Text-to-Speech (TTS) synthesis using deep learning relies on voice quality. Modern TTS models are advanced, but they need large amount of data. Given the growing computational complexity of these models and the scarcity of large,…

Sound · Computer Science 2023-10-10 Ze Liu

The utilization of discrete speech tokens, divided into semantic tokens and acoustic tokens, has been proven superior to traditional acoustic feature mel-spectrograms in terms of naturalness and robustness for text-to-speech (TTS)…

Sound · Computer Science 2024-03-29 Chenpeng Du , Yiwei Guo , Feiyu Shen , Zhijun Liu , Zheng Liang , Xie Chen , Shuai Wang , Hui Zhang , Kai Yu

In Task-Oriented Dialogue (TOD) systems, correctly updating the system's understanding of the user's requests (\textit{a.k.a} dialogue state tracking) is key to a smooth interaction. Traditionally, TOD systems perform this update in three…

Computation and Language · Computer Science 2024-07-02 Lucas Druart , Valentin Vielzeuf , Yannick Estève

While automatic speech recognition (ASR) systems have achieved remarkable performance with large-scale datasets, their efficacy remains inadequate in low-resource settings, encompassing dialects, accents, minority languages, and long-tail…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-23 Guanrou Yang , Fan Yu , Ziyang Ma , Zhihao Du , Zhifu Gao , Shiliang Zhang , Xie Chen

Recent prompt-based text-to-speech (TTS) models can clone an unseen speaker using only a short speech prompt. They leverage a strong in-context ability to mimic the speech prompts, including speaker style, prosody, and emotion. Therefore,…

Sound · Computer Science 2024-06-07 Jinlong Xue , Yayue Deng , Yingming Gao , Ya Li

Discourse markers ({\it by contrast}, {\it happily}, etc.) are words or phrases that are used to signal semantic and/or pragmatic relationships between clauses or sentences. Recent work has fruitfully explored the prediction of discourse…

Computation and Language · Computer Science 2020-06-03 Damien Sileo , Tim Van de Cruys , Camille Pradel , Philippe Muller

There has been a significant progress in Text-To-Speech (TTS) synthesis technology in recent years, thanks to the advancement in neural generative modeling. However, existing methods on any-speaker adaptive TTS have achieved unsatisfactory…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-15 Minki Kang , Dongchan Min , Sung Ju Hwang

Expressive text-to-speech (TTS) can synthesize a new speaking style by imiating prosody and timbre from a reference audio, which faces the following challenges: (1) The highly dynamic prosody information in the reference audio is difficult…

Sound · Computer Science 2022-11-07 Dongchao Yang , Songxiang Liu , Jianwei Yu , Helin Wang , Chao Weng , Yuexian Zou

Human communication involves more than explicit semantics, with implicit signals and contextual cues playing a critical role in shaping meaning. However, modern speech technologies, such as Automatic Speech Recognition (ASR) and…

Modern TTS systems designed for conversations achieve high-quality utterances but often remain inaccessible publicly. Are existing open-source architectures inadequate, or are current training techniques insufficient? This paper…

Computation and Language · Computer Science 2025-05-13 Hyouin Liu , Zhikuan Zhang

Automatic speech recognition (ASR) system is becoming a ubiquitous technology. Although its accuracy is closing the gap with that of human level under certain settings, one area that can further improve is to incorporate user-specific…

Computation and Language · Computer Science 2020-05-05 Young Mo Kang , Yingbo Zhou

We present a neural text-to-speech (TTS) method that models natural vocal effort variation to improve the intelligibility of synthetic speech in the presence of noise. The method consists of first measuring the spectral tilt of unlabeled…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-30 Tuomo Raitio , Petko Petkov , Jiangchuan Li , Muhammed Shifas , Andrea Davis , Yannis Stylianou

Cross-attention is a core mechanism in encoder-decoder architectures, widespread in many fields, including speech-to-text (S2T) processing. Its scores have been repurposed for various downstream applications--such as timestamp estimation…

Computation and Language · Computer Science 2025-09-23 Sara Papi , Dennis Fucci , Marco Gaido , Matteo Negri , Luisa Bentivogli

While automatic response generation for building chatbot systems has drawn a lot of attention recently, there is limited understanding on when we need to consider the linguistic context of an input text in the generation process. The task…

Computation and Language · Computer Science 2016-11-04 Chaozhuo Li , Yu Wu , Wei Wu , Chen Xing , Zhoujun Li , Ming Zhou