Daisy-TTS: Simulating Wider Spectrum of Emotions via Prosody Embedding Decomposition

• URL: http://arxiv.org/abs/2402.14523v2
• Date: Thu, 27 Jun 2024 15:14:58 GMT
• Title: Daisy-TTS: Simulating Wider Spectrum of Emotions via Prosody Embedding Decomposition
• Authors: Rendi Chevi, Alham Fikri Aji,
• Abstract summary: We propose an emotional text-to-speech design to simulate a wider spectrum of emotions grounded on the structural model. Our proposed design, Daisy-TTS, incorporates a prosody encoder to learn emotionally-separable prosody embedding as a proxy for emotion.
• Score: 12.605375307094416
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We often verbally express emotions in a multifaceted manner, they may vary in their intensities and may be expressed not just as a single but as a mixture of emotions. This wide spectrum of emotions is well-studied in the structural model of emotions, which represents variety of emotions as derivative products of primary emotions with varying degrees of intensity. In this paper, we propose an emotional text-to-speech design to simulate a wider spectrum of emotions grounded on the structural model. Our proposed design, Daisy-TTS, incorporates a prosody encoder to learn emotionally-separable prosody embedding as a proxy for emotion. This emotion representation allows the model to simulate: (1) Primary emotions, as learned from the training samples, (2) Secondary emotions, as a mixture of primary emotions, (3) Intensity-level, by scaling the emotion embedding, and (4) Emotions polarity, by negating the emotion embedding. Through a series of perceptual evaluations, Daisy-TTS demonstrated overall higher emotional speech naturalness and emotion perceiveability compared to the baseline.

Related papers

• EmoSphere-TTS: Emotional Style and Intensity Modeling via Spherical Emotion Vector for Controllable Emotional Text-to-Speech [34.03787613163788]
  EmoSphere-TTS synthesizes expressive emotional speech by using a spherical emotion vector to control the emotional style and intensity of the synthetic speech. We propose a dual conditional adversarial network to improve the quality of generated speech by reflecting the multi-aspect characteristics.
  arXiv  Detail & Related papers  (2024-06-12T01:40:29Z)
• emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation [42.29118614670941]
  We propose emotion2vec, a universal speech emotion representation model. emotion2vec is pre-trained on unlabeled emotion data through self-supervised online distillation. It outperforms state-of-the-art pre-trained universal models and emotion specialist models.
  arXiv  Detail & Related papers  (2023-12-23T07:46:55Z)
• Emotion Rendering for Conversational Speech Synthesis with Heterogeneous Graph-Based Context Modeling [50.99252242917458]
  Conversational Speech Synthesis (CSS) aims to accurately express an utterance with the appropriate prosody and emotional inflection within a conversational setting. To address the issue of data scarcity, we meticulously create emotional labels in terms of category and intensity. Our model outperforms the baseline models in understanding and rendering emotions.
  arXiv  Detail & Related papers  (2023-12-19T08:47:50Z)
• Speech Synthesis with Mixed Emotions [77.05097999561298]
  We propose a novel formulation that measures the relative difference between the speech samples of different emotions. We then incorporate our formulation into a sequence-to-sequence emotional text-to-speech framework. At run-time, we control the model to produce the desired emotion mixture by manually defining an emotion attribute vector.
  arXiv  Detail & Related papers  (2022-08-11T15:45:58Z)
• Emotion Intensity and its Control for Emotional Voice Conversion [77.05097999561298]
  Emotional voice conversion (EVC) seeks to convert the emotional state of an utterance while preserving the linguistic content and speaker identity. In this paper, we aim to explicitly characterize and control the intensity of emotion. We propose to disentangle the speaker style from linguistic content and encode the speaker style into a style embedding in a continuous space that forms the prototype of emotion embedding.
  arXiv  Detail & Related papers  (2022-01-10T02:11:25Z)
• Emotion Recognition from Multiple Modalities: Fundamentals and Methodologies [106.62835060095532]
  We discuss several key aspects of multi-modal emotion recognition (MER) We begin with a brief introduction on widely used emotion representation models and affective modalities. We then summarize existing emotion annotation strategies and corresponding computational tasks. Finally, we outline several real-world applications and discuss some future directions.
  arXiv  Detail & Related papers  (2021-08-18T21:55:20Z)
• Emotion Recognition under Consideration of the Emotion Component Process Model [9.595357496779394]
  We use the emotion component process model (CPM) by Scherer (2005) to explain emotion communication. CPM states that emotions are a coordinated process of various subcomponents, in reaction to an event, namely the subjective feeling, the cognitive appraisal, the expression, a physiological bodily reaction, and a motivational action tendency. We find that emotions on Twitter are predominantly expressed by event descriptions or subjective reports of the feeling, while in literature, authors prefer to describe what characters do, and leave the interpretation to the reader.
  arXiv  Detail & Related papers  (2021-07-27T15:53:25Z)
• A Circular-Structured Representation for Visual Emotion Distribution Learning [82.89776298753661]
  We propose a well-grounded circular-structured representation to utilize the prior knowledge for visual emotion distribution learning. To be specific, we first construct an Emotion Circle to unify any emotional state within it. On the proposed Emotion Circle, each emotion distribution is represented with an emotion vector, which is defined with three attributes.
  arXiv  Detail & Related papers  (2021-06-23T14:53:27Z)
• Enhancing Cognitive Models of Emotions with Representation Learning [58.2386408470585]
  We present a novel deep learning-based framework to generate embedding representations of fine-grained emotions. Our framework integrates a contextualized embedding encoder with a multi-head probing model. Our model is evaluated on the Empathetic Dialogue dataset and shows the state-of-the-art result for classifying 32 emotions.
  arXiv  Detail & Related papers  (2021-04-20T16:55:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.