中文
相关论文

相关论文: Phone-Level Prosody Modelling with GMM-Based MDN f…

200 篇论文

Generating natural speech with diverse and smooth prosody pattern is a challenging task. Although random sampling with phone-level prosody distribution has been investigated to generate different prosody patterns, the diversity of the…

声音 · 计算机科学 2023-10-03 Chenpeng Du , Kai Yu

Unlike human speakers, typical text-to-speech (TTS) systems are unable to produce multiple distinct renditions of a given sentence. This has previously been addressed by adding explicit external control. In contrast, generative models are…

音频与语音处理 · 电气工程与系统科学 2020-11-04 Zack Hodari , Oliver Watts , Simon King

Speech pre-training has primarily demonstrated efficacy on classification tasks, while its capability of generating novel speech, similar to how GPT-2 can generate coherent paragraphs, has barely been explored. Generative Spoken Language…

We propose a versatile feedback scheme for both single- and multi-user multiple-input multiple-output (MIMO) frequency division duplex (FDD) systems. Particularly, we propose utilizing a Gaussian mixture model (GMM) with a reduced number of…

信息论 · 计算机科学 2023-11-29 Nurettin Turan , Benedikt Fesl , Michael Koller , Michael Joham , Wolfgang Utschick

Spontaneous speech has many affective and pragmatic functions that are interesting and challenging to model in TTS. However, the presence of reduced articulation, fillers, repetitions, and other disfluencies in spontaneous speech make the…

音频与语音处理 · 电气工程与系统科学 2023-06-02 Harm Lameris , Shivam Mehta , Gustav Eje Henter , Joakim Gustafson , Éva Székely

Recent neural speech synthesis systems have gradually focused on the control of prosody to improve the quality of synthesized speech, but they rarely consider the variability of prosody and the correlation between prosody and semantics…

音频与语音处理 · 电气工程与系统科学 2020-08-14 Zhen Zeng , Jianzong Wang , Ning Cheng , Jing Xiao

Text-to-Speech (TTS) has recently seen great progress in synthesizing high-quality speech owing to the rapid development of parallel TTS systems, but producing speech with naturalistic prosodic variations, speaking styles and emotional…

音频与语音处理 · 电气工程与系统科学 2023-11-21 Yinghao Aaron Li , Cong Han , Nima Mesgarani

Recent advances in text-to-speech, particularly those based on Graph Neural Networks (GNNs), have significantly improved the expressiveness of short-form synthetic speech. However, generating human-parity long-form speech with high dynamic…

声音 · 计算机科学 2023-10-10 Dake Guo , Xinfa Zhu , Liumeng Xue , Tao Li , Yuanjun Lv , Yuepeng Jiang , Lei Xie

Spontaneous style speech synthesis, which aims to generate human-like speech, often encounters challenges due to the scarcity of high-quality data and limitations in model capabilities. Recent language model-based TTS systems can be trained…

声音 · 计算机科学 2024-07-19 Weiqin Li , Peiji Yang , Yicheng Zhong , Yixuan Zhou , Zhisheng Wang , Zhiyong Wu , Xixin Wu , Helen Meng

With the rapid advancement in deep generative models, recent neural Text-To-Speech(TTS) models have succeeded in synthesizing human-like speech. There have been some efforts to generate speech with various prosody beyond monotonous prosody…

音频与语音处理 · 电气工程与系统科学 2023-10-24 Seongho Joo , Hyukhun Koh , Kyomin Jung

Although word-level prosody modeling in neural text-to-speech (TTS) has been investigated in recent research for diverse speech synthesis, it is still challenging to control speech synthesis manually without a specific reference. This is…

音频与语音处理 · 电气工程与系统科学 2022-02-17 Yiwei Guo , Chenpeng Du , Kai Yu

Recent advances in Text-to-Speech (TTS) have improved quality and naturalness to near-human capabilities when considering isolated sentences. But something which is still lacking in order to achieve human-like communication is the dynamic…

计算与语言 · 计算机科学 2021-04-21 Shubhi Tyagi , Marco Nicolis , Jonas Rohnke , Thomas Drugman , Jaime Lorenzo-Trueba

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…

声音 · 计算机科学 2022-10-25 Florian Lux , Julia Koch , Ngoc Thang Vu

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.…

计算与语言 · 计算机科学 2023-09-20 Atli Thor Sigurgeirsson , Simon King

Modern sequence to sequence neural TTS systems provide close to natural speech quality. Such systems usually comprise a network converting linguistic/phonetic features sequence to an acoustic features sequence, cascaded with a neural…

音频与语音处理 · 电气工程与系统科学 2019-09-26 Slava Shechtman , Alex Sorin

The quest for comprehensive generative models of intonation that link linguistic and paralinguistic functions to prosodic forms has been a longstanding challenge of speech communication research. Traditional intonation models have given way…

音频与语音处理 · 电气工程与系统科学 2019-03-19 Branislav Gerazov , Gérard Bailly , Omar Mohammed , Yi Xu , Philip N. Garner

Expressive text-to-speech (TTS) has become a hot research topic recently, mainly focusing on modeling prosody in speech. Prosody modeling has several challenges: 1) the extracted pitch used in previous prosody modeling works have inevitable…

音频与语音处理 · 电气工程与系统科学 2022-02-17 Yi Ren , Ming Lei , Zhiying Huang , Shiliang Zhang , Qian Chen , Zhijie Yan , Zhou Zhao

Recently, a versatile limited feedback scheme based on a Gaussian mixture model (GMM) was proposed for frequency division duplex (FDD) systems. This scheme provides high flexibility regarding various system parameters and is applicable to…

信息论 · 计算机科学 2023-11-29 Nurettin Turan , Benedikt Fesl , Wolfgang Utschick

Cross-speaker style transfer is crucial to the applications of multi-style and expressive speech synthesis at scale. It does not require the target speakers to be experts in expressing all styles and to collect corresponding recordings for…

声音 · 计算机科学 2021-07-28 Shifeng Pan , Lei He

In NLP, text language models based on words or subwords are known to outperform their character-based counterparts. Yet, in the speech community, the standard input of spoken LMs are 20ms or 40ms-long discrete units (shorter than a…

计算与语言 · 计算机科学 2023-10-10 Robin Algayres , Yossi Adi , Tu Anh Nguyen , Jade Copet , Gabriel Synnaeve , Benoit Sagot , Emmanuel Dupoux
‹ 上一页 1 2 3 10 下一页 ›