# PSP: An Interpretable Per-Dimension Accent Benchmark for Indic Text-to-Speech

arXiv: https://arxiv.org/abs/2604.25476 · HTML: https://mlsanity.com/paper/2604.25476/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 20 references that are in the map.
- First posted on arXiv 28 Apr 2026.

## Builds on (most cited first, 9 of 9)

- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech](https://mlsanity.com/paper/2205.12446/) (2022)
- [UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022](https://mlsanity.com/paper/2204.02152/) (2022)
- [The VoiceMOS Challenge 2022](https://mlsanity.com/paper/2203.11389/) (2022)
- [Towards Building ASR Systems for the Next Billion Users](https://mlsanity.com/paper/2111.03945/) (2021)
- [Towards Building Text-To-Speech Systems for the Next Billion Users](https://mlsanity.com/paper/2211.09536/) (2022)
- [Pairwise Evaluation of Accent Similarity in Speech Synthesis](https://mlsanity.com/paper/2505.14410/) (2025)
- [Quantifying Speaker Embedding Phonological Rule Interactions in Accented Speech Synthesis](https://mlsanity.com/paper/2601.14417/) (2026)
- [Learning-free L2-Accented Speech Generation using Phonological Rules](https://mlsanity.com/paper/2603.07550/) (2026)

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

- [LASE: Language-Adversarial Speaker Encoding for Indic Cross-Script Identity Preservation](https://mlsanity.com/paper/2605.00777/) (2026)

## Abstract (arXiv)

Standard text-to-speech (TTS) evaluation measures intelligibility (WER, CER) and overall naturalness (MOS, UTMOS) but does not quantify accent. A synthesiser may score well on all four yet sound non-native on features that are phonemic in the target language. For Indic languages, these features include retroflex articulation, aspiration, vowel length, and the Tamil retroflex approximant (letter zha). We present PSP, the Phoneme Substitution Profile, an interpretable, per-phonological-dimension accent benchmark for Indic TTS. PSP decomposes accent into six complementary dimensions: retroflex collapse rate (RR), aspiration fidelity (AF), vowel-length fidelity (LF), Tamil-zha fidelity (ZF), Frechet Audio Distance (FAD), and prosodic signature divergence (PSD). The first four are measured via forced alignment plus native-speaker-centroid acoustic probes over Wav2Vec2-XLS-R layer-9 embeddings; the latter two are corpus-level distributional distances. In this v1 we benchmark four commercial and open-source systems (ElevenLabs v3, Cartesia Sonic-3, Sarvam Bulbul, Indic Parler-TTS) on Hindi, Telugu, and Tamil pilot sets, with a fifth system (Praxy Voice) included on all three languages, plus an R5->R6 case study on Telugu. Three findings: (i) retroflex collapse grows monotonically with phonological difficulty Hindi < Telugu < Tamil (~1%, ~40%, ~68%); (ii) PSP ordering diverges from WER ordering -- commercial WER-leaders do not uniformly lead on retroflex or prosodic fidelity; (iii) no single system is Pareto-optimal across all six dimensions. We release native reference centroids (500 clips per language), 1000-clip embeddings for FAD, 500-clip prosodic feature matrices for PSD, 300-utterance golden sets per language, scoring code under MIT, and centroids under CC-BY. Formal MOS-correlation is deferred to v2; v1 reports five internal-consistency signals plus a native-audio sanity check.