# Investigation for Relative Voice Impression Estimation

arXiv: https://arxiv.org/abs/2602.14172 · HTML: https://mlsanity.com/paper/2602.14172/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 40 references that are in the map.
- First posted on arXiv 15 Feb 2026.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022](https://mlsanity.com/paper/2204.02152/) (2022)
- [Self-Supervised Speech Representation Learning: A Review](https://mlsanity.com/paper/2205.10643/) (2022)
- [Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2311.13165/) (2023)
- [Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning](https://mlsanity.com/paper/2406.11161/) (2024)
- [Why does Self-Supervised Learning for Speech Recognition Benefit Speaker Recognition?](https://mlsanity.com/paper/2204.12765/) (2022)
- [Feed-Forward Networks with Attention Can Solve Some Long-Term Memory Problems](https://mlsanity.com/paper/1512.08756/) (2015)
- [End-to-End Integration of Speech Recognition, Speech Enhancement, and Self-Supervised Learning Representation](https://mlsanity.com/paper/2204.00540/) (2022)
- [Audio-Aware Large Language Models as Judges for Speaking Styles](https://mlsanity.com/paper/2506.05984/) (2025)
- [SpeechLLM-as-Judges: Towards General and Interpretable Speech Quality Evaluation](https://mlsanity.com/paper/2510.14664/) (2025)
- [Zero-shot text-to-speech synthesis conditioned using self-supervised speech representation model](https://mlsanity.com/paper/2304.11976/) (2023)
- [OmniVox: Zero-Shot Emotion Recognition with Omni-LLMs](https://mlsanity.com/paper/2503.21480/) (2025)
- [Voice Impression Control in Zero-Shot TTS](https://mlsanity.com/paper/2506.05688/) (2025)
- [The Voice Timbre Attribute Detection 2025 Challenge Evaluation Plan](https://mlsanity.com/paper/2505.09382/) (2025)
- [Multi-interaction TTS toward professional recording reproduction](https://mlsanity.com/paper/2507.00808/) (2025)
- [Interpretable Audio Editing Evaluation via Chain-of-Thought Difference-Commonality Reasoning with Multimodal LLMs](https://mlsanity.com/paper/2509.16975/) (2025)

## Built on by (most cited first, 1 of 1)

- [Scalable Direction-Following TTS via Voice Impression-Guided Pseudo Triplet Construction](https://mlsanity.com/paper/2609.02623/) (2026)

## Abstract (arXiv)

Paralinguistic and non-linguistic aspects of speech strongly influence listener impressions. While most research focuses on absolute impression scoring, this study investigates relative voice impression estimation (RIE), a framework for predicting the perceptual difference between two utterances from the same speaker. The estimation target is a low-dimensional vector derived from subjective evaluations, quantifying the perceptual shift of the second utterance relative to the first along an antonymic axis (e.g., ``Dark--Bright''). To isolate expressive and prosodic variation, we used recordings of a professional speaker reading a text in various styles. We compare three modeling approaches: classical acoustic features commonly used for speech emotion recognition, self-supervised speech representations, and multimodal large language models (MLLMs). Our results demonstrate that models using self-supervised representations outperform methods with classical acoustic features, particularly in capturing complex and dynamic impressions (e.g., ``Cold--Warm'') where classical features fail. In contrast, current MLLMs prove unreliable for this fine-grained pairwise task. This study provides the first systematic investigation of RIE and demonstrates the strength of self-supervised speech models in capturing subtle perceptual variations.