English
Related papers

Related papers: CLAPSpeech: Learning Prosody from Text Context wit…

200 papers

Reference-based Text-to-Speech (TTS) models can generate multiple, prosodically-different renditions of the same target text. Such models jointly learn a latent acoustic space during training, which can be sampled from during inference.…

Computation and Language · Computer Science 2023-09-20 Atli Thor Sigurgeirsson , Simon King

Recent work has studied text-to-audio synthesis using large amounts of paired text-audio data. However, audio recordings with high-quality text annotations can be difficult to acquire. In this work, we approach text-to-audio synthesis using…

Prosodic boundary plays an important role in text-to-speech synthesis (TTS) in terms of naturalness and readability. However, the acquisition of prosodic boundary labels relies on manual annotation, which is costly and time-consuming. In…

Sound · Computer Science 2022-06-17 Ziqian Dai , Jianwei Yu , Yan Wang , Nuo Chen , Yanyao Bian , Guangzhi Li , Deng Cai , Dong Yu

Prosody contains rich information beyond the literal meaning of words, which is crucial for the intelligibility of speech. Current models still fall short in phrasing and intonation; they not only miss or misplace breaks when synthesizing…

Computation and Language · Computer Science 2024-12-20 Xiangheng He , Junjie Chen , Zixing Zhang , Björn W. Schuller

Prosody transfer is well-studied in the context of expressive speech synthesis. Cross-lingual prosody transfer, however, is challenging and has been under-explored to date. In this paper, we present a novel solution to learn prosody…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-21 Jakub Swiatkowski , Duo Wang , Mikolaj Babianski , Patrick Lumban Tobing , Ravichander Vipperla , Vincent Pollet

Modern natural language processing (NLP) methods employ self-supervised pretraining objectives such as masked language modeling to boost the performance of various application tasks. These pretraining methods are frequently extended with…

Computation and Language · Computer Science 2021-02-26 Nils Rethmeier , Isabelle Augenstein

This study introduces CLASP (Contrastive Language-Speech Pretraining), a multilingual, multimodal representation tailored for audio-text information retrieval. CLASP leverages the synergy between spoken content and textual data. During…

Computation and Language · Computer Science 2025-03-25 Mohammad Mahdi Abootorabi , Ehsaneddin Asgari

Recent research demonstrates the effectiveness of using pretrained language models (PLM) to improve dense retrieval and multilingual dense retrieval. In this work, we present a simple but effective monolingual pretraining task called…

Information Retrieval · Computer Science 2022-06-08 Ning Wu , Yaobo Liang , Houxing Ren , Linjun Shou , Nan Duan , Ming Gong , Daxin Jiang

The field of prosody transfer in speech synthesis systems is rapidly advancing. This research is focused on evaluating learning methods for adapting pre-trained monolingual text-to-speech (TTS) models to multilingual conditions, i.e.,…

Computation and Language · Computer Science 2024-06-19 Arnav Goel , Medha Hira , Anubha Gupta

Lip-to-speech synthesis aims to generate speech audio directly from silent facial video by reconstructing linguistic content from lip movements, providing valuable applications in situations where audio signals are unavailable or degraded.…

Sound · Computer Science 2026-02-03 Jaejun Lee , Yoori Oh , Kyogu Lee

Generating expressive speech with rich and varied prosody continues to be a challenge for Text-to-Speech. Most efforts have focused on sophisticated neural architectures intended to better model the data distribution. Yet, in evaluations it…

The cloning of a speaker's voice using an untranscribed reference sample is one of the great advances of modern neural text-to-speech (TTS) methods. Approaches for mimicking the prosody of a transcribed reference audio have also been…

Sound · Computer Science 2022-10-25 Florian Lux , Julia Koch , Ngoc Thang Vu

The recent progress in non-autoregressive text-to-speech (NAR-TTS) has made fast and high-quality speech synthesis possible. However, current NAR-TTS models usually use phoneme sequence as input and thus cannot understand the…

Sound · Computer Science 2022-04-26 Zhenhui Ye , Zhou Zhao , Yi Ren , Fei Wu

In voice conversion (VC), an approach showing promising results in the latest voice conversion challenge (VCC) 2020 is to first use an automatic speech recognition (ASR) model to transcribe the source speech into the underlying linguistic…

Sound · Computer Science 2021-07-21 Wen-Chin Huang , Tomoki Hayashi , Xinjian Li , Shinji Watanabe , Tomoki Toda

The prosody of a spoken word is determined by its surrounding context. In incremental text-to-speech synthesis, where the synthesizer produces an output before it has access to the complete input, the full context is often unknown which can…

Computation and Language · Computer Science 2021-06-16 Brooke Stephenson , Thomas Hueber , Laurent Girin , Laurent Besacier

Text-to-speech is now able to achieve near-human naturalness and research focus has shifted to increasing expressivity. One popular method is to transfer the prosody from a reference speech sample. There have been considerable advances in…

Audio and Speech Processing · Electrical Eng. & Systems 2021-07-22 Alexandra Torresquintero , Tian Huey Teh , Christopher G. R. Wallis , Marlene Staib , Devang S Ram Mohan , Vivian Hu , Lorenzo Foglianti , Jiameng Gao , Simon King

A text-to-speech (TTS) model trained to reconstruct speech given text tends towards predictions that are close to the average characteristics of a dataset, failing to model the variations that make human speech sound natural. This problem…

Audio and Speech Processing · Electrical Eng. & Systems 2024-08-29 John Janiczek , Dading Chong , Dongyang Dai , Arlo Faria , Chao Wang , Tao Wang , Yuzong Liu

Text-to-speech (TTS) systems that scale up the amount of training data have achieved significant improvements in zero-shot speech synthesis. However, these systems have certain limitations: they require a large amount of training data,…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-07 Taejun Bak , Youngsik Eom , SeungJae Choi , Young-Sun Joo

Multilingual generative models obtain remarkable cross-lingual in-context learning capabilities through pre-training on large-scale corpora. However, they still exhibit a performance bias toward high-resource languages and learn isolated…

Computation and Language · Computer Science 2024-06-13 Chong Li , Shaonan Wang , Jiajun Zhang , Chengqing Zong

Lyrics alignment gained considerable attention in recent years. State-of-the-art systems either re-use established speech recognition toolkits, or design end-to-end solutions involving a Connectionist Temporal Classification (CTC) loss.…

Sound · Computer Science 2023-06-14 Simon Durand , Daniel Stoller , Sebastian Ewert