# Investigating the Reasonable Effectiveness of Speaker Pre-Trained Models and their Synergistic Power for SingMOS Prediction

arXiv: https://arxiv.org/abs/2506.02232 · HTML: https://mlsanity.com/paper/2506.02232/

## Key facts

- Cited by 1 papers in the map (data through 20 Oct 2026).
- Placed in Vocoders and speech synthesis, one of 11 directions in Speech and audio language models.
- Builds on 19 of its 24 references that are in the map.
- First posted on arXiv 2 Jun 2025.

## Placed in

- Speech and audio language models / [Vocoders and speech synthesis](https://mlsanity.com/speech/vocoders-and-speech-synthesis/)

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

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training](https://mlsanity.com/paper/2306.00107/) (2023)
- [UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training](https://mlsanity.com/paper/2110.05752/) (2021)
- [SOMOS: The Samsung Open MOS Dataset for the Evaluation of Neural Text-to-Speech Synthesis](https://mlsanity.com/paper/2204.03040/) (2022)
- [MAP-Music2Vec: A Simple and Effective Baseline for Self-Supervised Music Audio Representation Learning](https://mlsanity.com/paper/2212.02508/) (2022)
- [Heterogeneity over Homogeneity: Investigating Multilingual Speech Pre-Trained Models for Detecting Audio Deepfake](https://mlsanity.com/paper/2404.00809/) (2024)
- [MOS-Bench: Benchmarking Generalization Abilities of Subjective Speech Quality Assessment Models](https://mlsanity.com/paper/2411.03715/) (2024)
- [The VoiceMOS Challenge 2023: Zero-shot Subjective Speech Quality Prediction for Multiple Domains](https://mlsanity.com/paper/2310.02640/) (2023)
- [A Study on Incorporating Whisper for Robust Speech Assessment](https://mlsanity.com/paper/2309.12766/) (2023)
- [SingMOS: An extensive Open-Source Singing Voice Dataset for MOS Prediction](https://mlsanity.com/paper/2406.10911/) (2024)
- [Fusion of Self-supervised Learned Models for MOS Prediction](https://mlsanity.com/paper/2204.04855/) (2022)
- [Investigation of Ensemble features of Self-Supervised Pretrained Models for Automatic Speech Recognition](https://mlsanity.com/paper/2206.05518/) (2022)
- [Investigating Content-Aware Neural Text-To-Speech MOS Prediction Using Prosodic and Linguistic Features](https://mlsanity.com/paper/2211.00342/) (2022)
- [LE-SSL-MOS: Self-Supervised Learning MOS Prediction with Listener Enhancement](https://mlsanity.com/paper/2311.10656/) (2023)

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

- [Indic-CodecFake meets SATYAM: Towards Detecting Neural Audio Codec Synthesized Speech Deepfakes in Indic Languages](https://mlsanity.com/paper/2604.19949/) (2026)

## Abstract (arXiv)

In this study, we focus on Singing Voice Mean Opinion Score (SingMOS) prediction. Previous research have shown the performance benefit with the use of state-of-the-art (SOTA) pre-trained models (PTMs). However, they haven't explored speaker recognition speech PTMs (SPTMs) such as x-vector, ECAPA and we hypothesize that it will be the most effective for SingMOS prediction. We believe that due to their speaker recognition pre-training, it equips them to capture fine-grained vocal features (e.g., pitch, tone, intensity) from synthesized singing voices in a much more better way than other PTMs. Our experiments with SOTA PTMs including SPTMs and music PTMs validates the hypothesis. Additionally, we introduce a novel fusion framework, BATCH that uses Bhattacharya Distance for fusion of PTMs. Through BATCH with the fusion of speaker recognition SPTMs, we report the topmost performance comparison to all the individual PTMs and baseline fusion techniques as well as setting SOTA.