# Task Vector in TTS: Toward Emotionally Expressive Dialectal Speech Synthesis

arXiv: https://arxiv.org/abs/2512.18699 · HTML: https://mlsanity.com/paper/2512.18699/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 28 references that are in the map.
- First posted on arXiv 21 Dec 2025.

## Builds on (most cited first, 28 of 28)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://mlsanity.com/paper/2410.06885/) (2024)
- [CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens](https://mlsanity.com/paper/2407.05407/) (2024)
- [Seed-TTS: A Family of High-Quality Versatile Speech Generation Models](https://mlsanity.com/paper/2406.02430/) (2024)
- [CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models](https://mlsanity.com/paper/2412.10117/) (2024)
- [NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models](https://mlsanity.com/paper/2403.03100/) (2024)
- [VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild](https://mlsanity.com/paper/2403.16973/) (2024)
- [Emotional Voice Conversion: Theory, Databases and ESD](https://mlsanity.com/paper/2105.14762/) (2021)
- [Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens](https://mlsanity.com/paper/2503.01710/) (2025)
- [IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech](https://mlsanity.com/paper/2506.21619/) (2025)
- [Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition](https://mlsanity.com/paper/2407.04675/) (2024)
- [Whoever Started the Interference Should End It: Guiding Data-Free Model Merging via Task Vectors](https://mlsanity.com/paper/2503.08099/) (2025)
- [Chat Vector: A Simple Approach to Equip LLMs with Instruction Following and Model Alignment in New Languages](https://mlsanity.com/paper/2310.04799/) (2023)
- [MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder](https://mlsanity.com/paper/2505.07916/) (2025)
- [EmoDiff: Intensity Controllable Emotional Text-to-Speech with Soft-Label Guidance](https://mlsanity.com/paper/2211.09496/) (2022)
- [CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speech](https://mlsanity.com/paper/2404.02781/) (2024)
- [EmoVoice: LLM-based Emotional Text-To-Speech Model with Freestyle Text Prompting](https://mlsanity.com/paper/2504.12867/) (2025)
- [3D-Speaker-Toolkit: An Open-Source Toolkit for Multimodal Speaker Verification and Diarization](https://mlsanity.com/paper/2403.19971/) (2024)
- [EmoSpeech: Guiding FastSpeech2 Towards Emotional Text to Speech](https://mlsanity.com/paper/2307.00024/) (2023)
- [Differentiable Reward Optimization for LLM based TTS system](https://mlsanity.com/paper/2507.05911/) (2025)
- [Task Arithmetic can Mitigate Synthetic-to-Real Gap in Automatic Speech Recognition](https://mlsanity.com/paper/2406.02925/) (2024)
- [DrawSpeech: Expressive Speech Synthesis Using Prosodic Sketches as Control Conditions](https://mlsanity.com/paper/2501.04256/) (2025)
- [Distilling a speech and music encoder with task arithmetic](https://mlsanity.com/paper/2505.13270/) (2025)
- [Bailing-TTS: Chinese Dialectal Speech Synthesis Towards Human-like Spontaneous Representation](https://mlsanity.com/paper/2408.00284/) (2024)
- [A Novel Chinese Dialect TTS Frontend with Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/2206.04922/) (2022)

## Built on by (most cited first, 3 of 3)

- [Habibi: Laying the Open-Source Foundation of Unified-Dialectal Arabic Speech Synthesis](https://mlsanity.com/paper/2601.13802/) (2026)
- [Accent Vector: Controllable Accent Manipulation for Multilingual TTS Without Accented Data](https://mlsanity.com/paper/2603.07534/) (2026)
- [ParaGeo: Decomposing Paralinguistic Variation into a Shared Latent Geometry](https://mlsanity.com/paper/2610.03125/) (2026)

## Abstract (arXiv)

Recent advances in text-to-speech (TTS) have yielded remarkable improvements in naturalness and intelligibility. Building on these achievements, research has increasingly shifted toward enhancing the expressiveness of generated speech, such as dialectal and emotional TTS. However, cross-style synthesis combining both dialect and emotion remains challenging and largely unexplored, mainly due to the scarcity of dialectal data with emotional labels. To address this, we propose Hierarchical Expressive Vector (HE-Vector), a two-stage method for Emotional Dialectal TTS. In the first stage, we construct different task vectors to model dialectal and emotional styles independently, and then enhance single-style synthesis by adjusting their weights, a method we refer to as Expressive Vector (E-Vector). For the second stage, we hierarchically integrate these vectors to achieve controllable emotionally expressive dialect synthesis without requiring jointly labeled data, corresponding to Hierarchical Expressive Vector (HE-Vector). Experimental results demonstrate that HE-Vectors achieve superior performance in dialect synthesis, and promising results in synthesizing emotionally expressive dialectal speech in a zero-shot setting.