{"total":33,"rows":[{"id":"2301.00591","title":"Analysing Discrete Self Supervised Speech Representation for Spoken Language Modeling","created":"2023-01-02","cited_by_count":47,"area":null},{"id":"2210.15759","title":"Self-supervised language learning from raw audio: Lessons from the Zero Resource Speech Challenge","created":"2022-10-27","cited_by_count":34,"area":null},{"id":"2403.16865","title":"Encoding of lexical tone in self-supervised models of spoken language","created":"2024-03-25","cited_by_count":23,"area":null},{"id":"2312.14069","title":"EmphAssess : a Prosodic Benchmark on Assessing Emphasis Transfer in Speech-to-Speech Models","created":"2023-12-21","cited_by_count":22,"area":null},{"id":"2305.12464","title":"Self-supervised Predictive Coding Models Encode Speaker and Phonetic Information in Orthogonal Subspaces","created":"2023-05-21","cited_by_count":20,"area":null},{"id":"2210.15386","title":"Opening the Black Box of wav2vec Feature Encoder","created":"2022-10-27","cited_by_count":18,"area":null},{"id":"2305.18957","title":"Wave to Syntax: Probing spoken language models for syntax","created":"2023-05-30","cited_by_count":18,"area":null},{"id":"2407.01130","title":"Cross-Lingual Transfer Learning for Speech Translation","created":"2024-07-01","cited_by_count":11,"area":null},{"id":"2411.17666","title":"How do Multimodal Foundation Models Encode Text and Speech? An Analysis of Cross-Lingual and Cross-Modal Representations","created":"2024-11-26","cited_by_count":9,"area":null},{"id":"2512.20308","title":"SpidR: Learning Fast and Stable Linguistic Units for Spoken Language Models Without Supervision","created":"2025-12-23","cited_by_count":8,"area":null},{"id":"2502.05389","title":"The Role of Prosody in Spoken Question Answering","created":"2025-02-08","cited_by_count":6,"area":null},{"id":"2505.22487","title":"Effective Context in Neural Speech Models","created":"2025-05-28","cited_by_count":5,"area":null},{"id":"2509.15655","title":"Layer-wise Minimal Pair Probing Reveals Contextual Grammatical-Conceptual Hierarchy in Speech Representations","created":"2025-09-19","cited_by_count":5,"area":null},{"id":"2511.21517","title":"Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translation","created":"2025-11-26","cited_by_count":5,"area":null},{"id":"2506.02172","title":"Different Speech Translation Models Encode and Translate Speaker Gender Differently","created":"2025-06-02","cited_by_count":3,"area":null},{"id":"2506.10855","title":"Analyzing the relationships between pretraining language, phonetic, tonal, and speaker information in self-supervised speech models","created":"2025-06-12","cited_by_count":3,"area":null},{"id":"2302.14055","title":"Phone and speaker spatial organization in self-supervised speech representations","created":"2023-02-24","cited_by_count":2,"area":null},{"id":"2306.00697","title":"How Generative Spoken Language Modeling Encodes Noisy Speech: Investigation from Phonetics to Syntactics","created":"2023-06-01","cited_by_count":2,"area":null},{"id":"2309.12712","title":"Big model only for hard audios: Sample dependent Whisper model selection for efficient inferences","created":"2023-09-22","cited_by_count":2,"area":null},{"id":"2405.08237","title":"A predictive learning model can simulate temporal dynamics and context effects found in neural representations of continuous speech","created":"2024-05-13","cited_by_count":2,"area":null},{"id":"2406.02009","title":"Phonetic Enhanced Language Modeling for Text-to-Speech Synthesis","created":"2024-06-04","cited_by_count":2,"area":null},{"id":"2506.02181","title":"Echoes of Phonetics: Unveiling Relevant Acoustic Cues for ASR via Feature Attribution","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2601.18617","title":"Emergence of Phonemic, Syntactic, and Semantic Representations in Artificial Neural Networks","created":"2026-01-26","cited_by_count":2,"area":null},{"id":"2305.18602","title":"From `Snippet-lects' to Doculects and Dialects: Leveraging Neural Representations of Speech for Placing Audio Signals in a Language Landscape","created":"2023-05-29","cited_by_count":1,"area":null},{"id":"2512.19612","title":"MauBERT: Universal Phonetic Inductive Biases for Few-Shot Acoustic Units Discovery","created":"2025-12-22","cited_by_count":1,"area":null},{"id":"2608.06409","title":"Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2608.19211","title":"Represented but Ignored: A Causal Account of Prosodic Underuse in Audio-Language Models","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2506.17542","title":"Probing for Phonology in Self-Supervised Speech Representations: A Case Study on Accent Perception","created":"2025-06-21","cited_by_count":0,"area":null},{"id":"2510.05696","title":"Sparse deepfake detection promotes better disentanglement","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2603.18612","title":"DiscoPhon: Benchmarking the Unsupervised Discovery of Phoneme Inventories With Discrete Speech Units","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2606.25459","title":"Probing in the Wild: A Case Study of Self-Supervised Speech Representations on Mandarin Sub-dialects with Unsupervised Articulatory Analysis","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2610.16273","title":"Deep Speech Representations Track Word Timing along a Low-Dimensional Circular Trajectory","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.18726","title":"Code-Switching Detection via Language-Selective Dimensions in Speech Foundation Models","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}