# PRiSM: Benchmarking Phone Realization in Speech Models

arXiv: https://arxiv.org/abs/2601.14046 · HTML: https://mlsanity.com/paper/2601.14046/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 74 references that are in the map.
- First posted on arXiv 20 Jan 2026.

## Builds on (most cited first, 30 of 40)

- [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)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [SUPERB: Speech processing Universal PERformance Benchmark](https://mlsanity.com/paper/2105.01051/) (2021)
- [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech](https://mlsanity.com/paper/2205.12446/) (2022)
- [On The Landscape of Spoken Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2504.08528/) (2025)
- [The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modeling](https://mlsanity.com/paper/2011.11588/) (2020)
- [Intermediate Loss Regularization for CTC-based Speech Recognition](https://mlsanity.com/paper/2102.03216/) (2021)
- [Universal Phone Recognition with a Multilingual Allophone System](https://mlsanity.com/paper/2002.11800/) (2020)
- [Simple and Effective Zero-shot Cross-lingual Phoneme Recognition](https://mlsanity.com/paper/2109.11680/) (2021)
- [Self-Supervised Speech Representations are More Phonetic than Semantic](https://mlsanity.com/paper/2406.08619/) (2024)
- [A Survey on Speech Large Language Models for Understanding](https://mlsanity.com/paper/2410.18908/) (2024)
- [Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks](https://mlsanity.com/paper/2411.05361/) (2024)
- [speechocean762: An Open-Source Non-native English Speech Corpus For Pronunciation Assessment](https://mlsanity.com/paper/2104.01378/) (2021)
- [ByT5 model for massively multilingual grapheme-to-phoneme conversion](https://mlsanity.com/paper/2204.03067/) (2022)
- [Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2505.15957/) (2025)
- [The Edinburgh International Accents of English Corpus: Towards the Democratization of English ASR](https://mlsanity.com/paper/2303.18110/) (2023)
- [BabySLM: language-acquisition-friendly benchmark of self-supervised spoken language models](https://mlsanity.com/paper/2306.01506/) (2023)
- [ASR2K: Speech Recognition for Around 2000 Languages without Audio](https://mlsanity.com/paper/2209.02842/) (2022)
- [The Accented English Speech Recognition Challenge 2020: Open Datasets, Tracks, Baselines, Results and Methods](https://mlsanity.com/paper/2102.10233/) (2021)
- [Phonotactic Complexity and its Trade-offs](https://mlsanity.com/paper/2005.03774/) (2020)
- [ZIPA: A family of efficient models for multilingual phone recognition](https://mlsanity.com/paper/2505.23170/) (2025)
- [What Can an Accent Identifier Learn? Probing Phonetic and Prosodic Information in a Wav2vec2-based Accent Identification Model](https://mlsanity.com/paper/2306.06524/) (2023)
- [Whistle: Data-Efficient Multilingual and Crosslingual Speech Recognition via Weakly Phonetic Supervision](https://mlsanity.com/paper/2406.02166/) (2024)
- [CR-CTC: Consistency regularization on CTC for improved speech recognition](https://mlsanity.com/paper/2410.05101/) (2024)
- [UltraSuite: A Repository of Ultrasound and Acoustic Data from Child Speech Therapy Sessions](https://mlsanity.com/paper/1907.00835/) (2019)
- [Self-Supervised Models of Speech Infer Universal Articulatory Kinematics](https://mlsanity.com/paper/2310.10788/) (2023)
- [EasyCall corpus: a dysarthric speech dataset](https://mlsanity.com/paper/2104.02542/) (2021)

## Built on by (most cited first, 4 of 4)

- [An Empirical Recipe for Universal Phone Recognition](https://mlsanity.com/paper/2603.29042/) (2026)
- [Multilingual Dysarthric Speech Assessment Using Universal Phone Recognition and Language-Specific Phonemic Contrast Modeling](https://mlsanity.com/paper/2601.21205/) (2026)
- [Phone Segmentation and Recognition through Phonological Activation Mapping](https://mlsanity.com/paper/2607.09020/) (2026)
- [MoLGE: Mixture of Language Group Experts for Efficient Scaling of Massively Multilingual Speech Recognition](https://mlsanity.com/paper/2607.24030/) (2026)

## Abstract (arXiv)

Phone recognition (PR) serves as the atomic interface for language-agnostic modeling for cross-lingual speech processing and phonetic analysis. Despite prolonged efforts in developing PR systems, current evaluations only measure surface-level transcription accuracy. We introduce PRiSM, the first open-source benchmark designed to expose blind spots in phonetic perception through intrinsic and extrinsic evaluation of PR systems. PRiSM standardizes transcription-based evaluation and assesses downstream utility in clinical, educational, and multilingual settings with transcription and representation probes. We find that diverse language exposure during training is key to PR performance, encoder-CTC models are the most stable, and specialized PR models still outperform Large Audio Language Models. PRiSM releases code, recipes, and datasets to move the field toward multilingual speech models with robust phonetic ability: https://github.com/changelinglab/prism.