Cover Image

Layer-wise Minimal Pair Probing Reveals Contextual Grammatical-Conceptual Hierarchy in Speech Representations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	He, Linyang, Wang, Qiaolin, Jiang, Xilin, Mesgarani, Nima
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SightSound-R1: Cross-Modal Reasoning Distillation from Vision to Audio Language Models
by: Wang, Qiaolin, et al.
Published: (2025)

Listen, Chat, and Remix: Text-Guided Soundscape Remixing for Enhanced Auditory Experience
by: Jiang, Xilin, et al.
Published: (2024)

Style-Talker: Finetuning Audio Language Model and Style-Based Text-to-Speech Model for Fast Spoken Dialogue Generation
by: Li, Yinghao Aaron, et al.
Published: (2024)

Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separation
by: Jiang, Xilin, et al.
Published: (2024)

Just ASR + LLM? A Study on Speech Large Language Models' Ability to Identify and Understand Speaker in Spoken Dialogue
by: Wu, Junkai, et al.
Published: (2024)

MeanFlow-TSE: One-Step Generative Target Speaker Extraction with Mean Flow
by: Shimizu, Riki, et al.
Published: (2025)

Bridging Ears and Eyes: Analyzing Audio and Visual Large Language Models to Humans in Visible Sound Recognition and Reducing Their Sensory Gap via Cross-Modal Distillation
by: Jiang, Xilin, et al.
Published: (2025)

StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion
by: Li, Yinghao Aaron, et al.
Published: (2024)

SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model
by: Shams, Siavash, et al.
Published: (2024)

DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis
by: Li, Yinghao Aaron, et al.
Published: (2025)

DeCoR: Defy Knowledge Forgetting by Predicting Earlier Audio Codes
by: Jiang, Xilin, et al.
Published: (2023)

Exploring Finetuned Audio-LLM on Heart Murmur Features
by: Florea, Adrian, et al.
Published: (2025)

Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesis
by: Jiang, Xilin, et al.
Published: (2024)

Conversational Speech Recognition by Learning Audio-textual Cross-modal Contextual Representation
by: Wei, Kun, et al.
Published: (2023)

Neuro2Semantic: A Transfer Learning Framework for Semantic Reconstruction of Continuous Language from Human Intracranial EEG
by: Shams, Siavash, et al.
Published: (2025)

PAC: Pronunciation-Aware Contextualized Large Language Model-based Automatic Speech Recognition
by: Fu, Li, et al.
Published: (2025)

ContextASR-Bench: A Massive Contextual Speech Recognition Benchmark
by: Wang, He, et al.
Published: (2025)

Enhancing Dialogue Speech Recognition with Robust Contextual Awareness via Noise Representation Learning
by: Lee, Wonjun, et al.
Published: (2024)

Speech Codec Probing from Semantic and Phonetic Perspectives
by: Shi, Xuan, et al.
Published: (2026)

Dynamic Encoder Size Based on Data-Driven Layer-wise Pruning for Speech Recognition
by: Xu, Jingjing, et al.
Published: (2024)

Evaluating Speech-to-Text x LLM x Text-to-Speech Combinations for AI Interview Systems
by: Allbert, Rumi, et al.
Published: (2025)

Sentence-wise Speech Summarization: Task, Datasets, and End-to-End Modeling with LM Knowledge Distillation
by: Matsuura, Kohei, et al.
Published: (2024)

Optimizing Contextual Speech Recognition Using Vector Quantization for Efficient Retrieval
by: Flemotomos, Nikolaos, et al.
Published: (2024)

Robust and Efficient Autoregressive Speech Synthesis with Dynamic Chunk-wise Prediction Policy
by: Li, Bohan, et al.
Published: (2025)

Emphasis Sensitivity in Speech Representations
by: Cassini, Shaun, et al.
Published: (2025)

Probing for Phonology in Self-Supervised Speech Representations: A Case Study on Accent Perception
by: Venkateswaran, Nitin, et al.
Published: (2025)

Contextualized Automatic Speech Recognition with Dynamic Vocabulary
by: Sudo, Yui, et al.
Published: (2024)

Improving Neural Biasing for Contextual Speech Recognition by Early Context Injection and Text Perturbation
by: Huang, Ruizhe, et al.
Published: (2024)

Learning Speech Representations with Variational Predictive Coding
by: Yeh, Sung-Lin, et al.
Published: (2025)

DeepSpeech models show Human-like Performance and Processing of Cochlear Implant Inputs
by: Steinhardt, Cynthia R., et al.
Published: (2024)

Sci-Phi: A Large Language Model Spatial Audio Descriptor
by: Jiang, Xilin, et al.
Published: (2025)

AV-data2vec: Self-supervised Learning of Audio-Visual Speech Representations with Contextualized Target Representations
by: Lian, Jiachen, et al.
Published: (2023)

Exploring SSL Discrete Speech Features for Zipformer-based Contextual ASR
by: Cui, Mingyu, et al.
Published: (2024)

Codec2Vec: Self-Supervised Speech Representation Learning Using Neural Speech Codecs
by: Tseng, Wei-Cheng, et al.
Published: (2025)

Beyond Decodability: Reconstructing Language Model Representations with an Encoding Probe
by: Shen, Gaofei, et al.
Published: (2026)

Contextualized Automatic Speech Recognition with Dynamic Vocabulary Prediction and Activation
by: Lin, Zhennan, et al.
Published: (2025)

AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
by: Jiang, Xilin, et al.
Published: (2026)

Entropy-based Coarse and Compressed Semantic Speech Representation Learning
by: Zuo, Jialong, et al.
Published: (2025)

Teaching Audio Models to Reason: A Unified Framework for Source- and Layer-wise Distillation
by: Yang, Runyan, et al.
Published: (2025)

OWSM-Biasing: Contextualizing Open Whisper-Style Speech Models for Automatic Speech Recognition with Dynamic Vocabulary
by: Sudo, Yui, et al.
Published: (2025)