mlsanityData to 14 Oct 2026

What Can an Accent Identifier Learn? Probing Phonetic and Prosodic Information in a Wav2vec2-based Accent Identification Model

arXiv 2306.06524 ↗First posted 10 Jun 2023eess.AS cs.CL cs.SDcited by 18

Not on the map. Why?

Abstract (arXiv)

This study is focused on understanding and quantifying the change in phoneme and prosody information encoded in the Self-Supervised Learning (SSL) model, brought by an accent identification (AID) fine-tuning task. This problem is addressed based on model probing. Specifically, we conduct a systematic layer-wise analysis of the representations of the Transformer layers on a phoneme correlation task, and a novel word-level prosody prediction task. We compare the probing performance of the pre-trained and fine-tuned SSL models. Results show that the AID fine-tuning task steers the top 2 layers to learn richer phoneme and prosody representation. These changes share some similarities with the effects of fine-tuning with an Automatic Speech Recognition task. In addition, we observe strong accent-specific phoneme representations in layer 9. To sum up, this study provides insights into the understanding of SSL features and their interactions with fine-tuning tasks.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Builds on 22 of its 43 references that are in the map. First posted on arXiv 10 Jun 2023.

Builds on

22 of 43 references.

References · 22

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  3. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  4. 2021SUPERB: Speech processing Universal PERformance Benchmarkcited by 666
  5. 2015Deep Speech 2: End-to-End Speech Recognition in English and Mandarincited by 451
  6. 2021SpeechBrain: A General-Purpose Speech Toolkitcited by 406
  7. 2021Layer-wise Analysis of a Self-supervised Speech Representation Modelcited by 298
  8. 2020Exploring wav2vec 2.0 on speaker verification and language identificationcited by 95
  9. 2021Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representationscited by 81
  10. 2022ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakerscited by 74
  11. 2022On the Utility of Self-supervised Models for Prosody-related Taskscited by 42
  12. 2017Analyzing Hidden Representations in End-to-End Automatic Speech Recognition Systemscited by 32
10 more
  1. 2020Probing Acoustic Representations for Phonetic Propertiescited by 26
  2. 2021The Accented English Speech Recognition Challenge 2020: Open Datasets, Tracks, Baselines, Results and Methodscited by 24
  3. 2021Improving Accent Identification and Accented Speech Recognition Under a Framework of Self-supervised Learningcited by 13
  4. 2022Probing Speech Emotion Recognition Transformers for Linguistic Knowledgecited by 13
  5. 2022Improving Mispronunciation Detection with Wav2vec2-based Momentum Pseudo-Labeling for Accentedness and Intelligibility Assessmentcited by 10
  6. 2022Speech-based emotion recognition with self-supervised models using attentive channel-wise correlations and label smoothingcited by 10
  7. 2018Convolutional Neural Networks and Language Embeddings for End-to-End Dialect Recognitioncited by 9
  8. 2022Silence is Sweeter Than Speech: Self-Supervised Model Using Silence to Store Speaker Informationcited by 7
  9. 2021Deep Learning For Prominence Detection In Children's Read Speechcited by 6
  10. 2021Accent Recognition with Hybrid Phonetic Featurescited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 3; 2025: 9; 2026: 5.

18 papers.

Sort:

By area:

  1. 2023What Do Self-Supervised Speech Models Know About Words?cited by 64
  2. 2024A layer-wise analysis of Mandarin and English suprasegmentals in SSL speech modelscited by 18
  3. 2024VoiceShop: A Unified Speech-to-Speech Framework for Identity-Preserving Zero-Shot Voice Editingcited by 7
  4. 2025Iterative refinement, not training objective, makes HuBERT behave differently from wav2vec 2.0cited by 4
  5. 2026PRiSM: Benchmarking Phone Realization in Speech Modelscited by 4
  6. 2025Different Speech Translation Models Encode and Translate Speaker Gender Differentlycited by 3
  7. 2025Analyzing the relationships between pretraining language, phonetic, tonal, and speaker information in self-supervised speech modelscited by 3
  8. 2025An Exploration of Mamba for Speech Self-Supervised Modelscited by 2
  9. 2026Accent Vector: Controllable Accent Manipulation for Multilingual TTS Without Accented Datacited by 2
  10. 2024Converting Anyone's Voice: End-to-End Expressive Voice Conversion with a Conditional Diffusion Modelcited by 1
  11. 2025Representation of perceived prosodic similarity of conversational feedbackcited by 1
  12. 2025Tone recognition in low-resource languages of North-East India: peeling the layers of SSL-based speech modelscited by 1
6 more
  1. 2025Probing for Phonology in Self-Supervised Speech Representations: A Case Study on Accent Perceptioncited by 0
  2. 2025Emphasis Sensitivity in Speech Representationscited by 0
  3. 2025Geolocation-Aware Robust Spoken Language Identificationcited by 0
  4. 2026ACES: Accent Subspaces for Coupling, Explanations, and Stress-Testing in Automatic Speech Recognitioncited by 0
  5. 2026Perceptual compensation for tonal context in self-supervised speech modelscited by 0
  6. 2026Layer-wise Probing of wav2vec 2.0 and Whisper for Consonant Cluster Reduction in African American Englishcited by 0