Results 11 to 20 of about 69,603 (339)
Right Hemisphere Regions Critical for Expression of Emotion Through Prosody
Frontiers in Neurology, 2018 Impaired expression of emotion through pitch, loudness, rate, and rhythm of speech (affective prosody) is common and disabling after right hemisphere (RH) stroke. These deficits impede all social interactions.
Sona Patel +6 more
doaj +2 more sources
Text-Free Prosody-Aware Generative Spoken Language Modeling [PDF]
Annual Meeting of the Association for Computational Linguistics, 2021 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 Modeling (GSLM) (
E. Kharitonov +10 more
semanticscholar +1 more source
On the Utility of Self-Supervised Models for Prosody-Related Tasks [PDF]
Spoken Language Technology Workshop, 2022 Self-Supervised Learning (SSL) from speech data has produced models that have achieved remarkable performance in many tasks, and that are known to implicitly represent many aspects of information latently present in speech signals.
Guan-Ting Lin +7 more
semanticscholar +1 more source
Prosospeech: Enhancing Prosody with Quantized Vector Pre-Training in Text-To-Speech [PDF]
IEEE International Conference on Acoustics, Speech, and Signal Processing, 2022 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 errors, which
Yi Ren +6 more
semanticscholar +1 more source
Prosody Is Not Identity: A Speaker Anonymization Approach Using Prosody Cloning
IEEE International Conference on Acoustics, Speech, and Signal Processing, 2023 Prosody is closely linked to the identity of a speaker, leading to individual pitch and intonation patterns. Therefore, it is challenging in speaker anonymization to generate speech utterances that both keep the original audio’s main prosodic structure ...
Sarina Meyer +5 more
semanticscholar +1 more source
Fully-Hierarchical Fine-Grained Prosody Modeling For Interpretable Speech Synthesis [PDF]
IEEE International Conference on Acoustics, Speech, and Signal Processing, 2020 This paper proposes a hierarchical, fine-grained and interpretable latent variable model for prosody based on the Tacotron 2 text-to-speech model. It achieves multi-resolution modeling of prosody by conditioning finer level representations on coarser ...
Guangzhi Sun +5 more
semanticscholar +1 more source
Generating Diverse and Natural Text-to-Speech Samples Using a Quantized Fine-Grained VAE and Autoregressive Prosody Prior [PDF]
IEEE International Conference on Acoustics, Speech, and Signal Processing, 2020 Recent neural text-to-speech (TTS) models with fine-grained latent features enable precise control of the prosody of synthesized speech. Such models typically incorporate a fine-grained variational autoencoder (VAE) structure, extracting latent features ...
Guangzhi Sun +7 more
semanticscholar +1 more source
CopyCat: Many-to-Many Fine-Grained Prosody Transfer for Neural Text-to-Speech [PDF]
Interspeech, 2020 Prosody Transfer (PT) is a technique that aims to use the prosody from a source audio as a reference while synthesising speech. Fine-grained PT aims at capturing prosodic aspects like rhythm, emphasis, melody, duration, and loudness, from a source audio ...
S. Karlapati +5 more
semanticscholar +1 more source
Speech Prosody in Mental Disorders
Annual Review of Linguistics, 2022 In response to uncovering brain mechanisms underlying vocal communication and searching for biomarkers for mental illnesses, speech prosody has been increasingly studied in recent years in multiple disciplines, including psycholinguistics.
Hongwei Ding, Yang Zhang
semanticscholar +1 more source
Hierarchical Prosody Modeling for Non-Autoregressive Speech Synthesis [PDF]
Spoken Language Technology Workshop, 2020 Prosody modeling is an essential component in modern text-to-speech (TTS) frameworks. By explicitly providing prosody features to the TTS model, the style of synthesized utterances can thus be controlled.
C. Chien, Hung-yi Lee
semanticscholar +1 more source