Related papers: Exploring emotional prototypes in a high dimension…
Emotional text-to-speech seeks to convey affect while preserving intelligibility and prosody, yet existing methods rely on coarse labels or proxy classifiers and receive only utterance-level feedback. We introduce Emotion-Aware Stepwise…
While controllable Text-to-Speech (TTS) has achieved notable progress, most existing methods remain limited to inter-utterance-level control, making fine-grained intra-utterance expression challenging due to their reliance on non-public…
With read-aloud speech synthesis achieving high naturalness scores, there is a growing research interest in synthesising spontaneous speech. However, human spontaneous face-to-face conversation has both spoken and non-verbal aspects (here,…
The aim of this workshop is two-fold. First, it aims to establish a research community focused on design and evaluation of synthetic speech (TTS) interfaces that are tailored not only to goal oriented tasks (e.g., food ordering, online…
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…
It is desirable for a text-to-speech system to take into account the environment where synthetic speech is presented, and provide appropriate context-dependent output to the user. In this paper, we present and compare various approaches for…
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…
In response generation task, proper sentimental expressions can obviously improve the human-like level of the responses. However, for real application in online systems, high QPS (queries per second, an indicator of the flow capacity of…
Several fully end-to-end text-to-speech (TTS) models have been proposed that have shown better performance compared to cascade models (i.e., training acoustic and vocoder models separately). However, they often generate unstable pitch…
Speech emotion conversion is the task of modifying the perceived emotion of a speech utterance while preserving the lexical content and speaker identity. In this study, we cast the problem of emotion conversion as a spoken language…
Tacotron-based end-to-end speech synthesis has shown remarkable voice quality. However, the rendering of prosody in the synthesized speech remains to be improved, especially for long sentences, where prosodic phrasing errors can occur…
Streaming TTS that receives streaming text is essential for interactive systems, yet this scheme faces two major challenges: unnatural prosody due to missing lookahead and long-form collapse due to unbounded context. We propose a…
We investigate hierarchical emotion distribution (ED) for achieving multi-level quantitative control of emotion rendering in text-to-speech synthesis (TTS). We introduce a novel multi-step hierarchical ED prediction module that quantifies…
A text-to-speech synthesis system typically consists of multiple stages, such as a text analysis frontend, an acoustic model and an audio synthesis module. Building these components often requires extensive domain expertise and may contain…
Emotion is not limited to discrete categories of happy, sad, angry, fear, disgust, surprise, and so on. Instead, each emotion category is projected into a set of nearly independent dimensions, named pleasure (or valence), arousal, and…
Understanding the reason for emotional support response is crucial for establishing connections between users and emotional support dialogue systems. Previous works mostly focus on generating better responses but ignore interpretability,…
Effective speech emotional representations play a key role in Speech Emotion Recognition (SER) and Emotional Text-To-Speech (TTS) tasks. However, emotional speech samples are more difficult and expensive to acquire compared with Neutral…
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…
End-to-end neural TTS has achieved superior performance on reading style speech synthesis. However, it's still a challenge to build a high-quality conversational TTS due to the limitations of the corpus and modeling capability. This study…
A recent trend in the domain of open-domain conversational agents is enabling them to converse empathetically to emotional prompts. Current approaches either follow an end-to-end approach or condition the responses on similar emotion labels…