Buchumschlag

Perception of Phonological Assimilation by Neural Speech Recognition Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Pouw, Charlotte, Kloots, Marianne de Heer, Alishahi, Afra, Zuidema, Willem
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Computation and Language
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

A Linguistically Motivated Analysis of Intonational Phrasing in Text-to-Speech Systems: Revealing Gaps in Syntactic Sensitivity
von: Pouw, Charlotte, et al.
Veröffentlicht: (2025)

In-Context Learning in Speech Language Models: Analyzing the Role of Acoustic Features, Linguistic Structure, and Induction Heads
von: Pouw, Charlotte, et al.
Veröffentlicht: (2026)

Human-like Linguistic Biases in Neural Speech Models: Phonetic Categorization and Phonotactic Constraints in Wav2Vec2.0
von: Kloots, Marianne de Heer, et al.
Veröffentlicht: (2024)

The Curious Case of Visual Grounding: Different Effects for Speech- and Text-based Language Encoders
von: Sauter, Adrian, et al.
Veröffentlicht: (2025)

Tracking the emergence of linguistic structure in self-supervised models learning from speech
von: Kloots, Marianne de Heer, et al.
Veröffentlicht: (2026)

What do self-supervised speech models know about Dutch? Analyzing advantages of language-specific pre-training
von: Kloots, Marianne de Heer, et al.
Veröffentlicht: (2025)

Linguists should learn to love speech-based deep learning models
von: Kloots, Marianne de Heer, et al.
Veröffentlicht: (2025)

Disentangling Textual and Acoustic Features of Neural Speech Representations
von: Mohebbi, Hosein, et al.
Veröffentlicht: (2024)

Vision-Language Models Align with Human Neural Representations in Concept Processing
von: Bavaresco, Anna, et al.
Veröffentlicht: (2024)

How Language Models Prioritize Contextual Grammatical Cues?
von: Amirzadeh, Hamidreza, et al.
Veröffentlicht: (2024)

Inherent Biases of Recurrent Neural Networks for Phonological Assimilation and Dissimilation
von: Doucette, Amanda
Veröffentlicht: (2017)

Multilingual Phonological Feature Recognition with Self-Supervised Speech Models
von: Hernandez, Abner, et al.
Veröffentlicht: (2026)

Are We Paying Attention to Her? Investigating Gender Disambiguation and Attention in Machine Translation
von: Manna, Chiara, et al.
Veröffentlicht: (2025)

Do Language Models Exhibit Human-like Structural Priming Effects?
von: Jumelet, Jaap, et al.
Veröffentlicht: (2024)

Exploring bat song syllable representations in self-supervised audio encoders
von: Kloots, Marianne de Heer, et al.
Veröffentlicht: (2024)

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

Gender Disambiguation in Machine Translation: Diagnostic Evaluation in Decoder-Only Architectures
von: Manna, Chiara, et al.
Veröffentlicht: (2026)

Black Big Boxes: Tracing Adjective Order Preferences in Large Language Models
von: Jumelet, Jaap, et al.
Veröffentlicht: (2024)

Encoding of lexical tone in self-supervised models of spoken language
von: Shen, Gaofei, et al.
Veröffentlicht: (2024)

On the reliability of feature attribution methods for speech classification
von: Shen, Gaofei, et al.
Veröffentlicht: (2025)

Language Complexity and Speech Recognition Accuracy: Orthographic Complexity Hurts, Phonological Complexity Doesn't
von: Taguchi, Chihiro, et al.
Veröffentlicht: (2024)

Phonology Recognition in American Sign Language
von: Tavella, Federico, et al.
Veröffentlicht: (2021)

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

Phonology-Guided Speech-to-Speech Translation for African Languages
von: Ochieng, Peter, et al.
Veröffentlicht: (2024)

Quantifying Speaker Embedding Phonological Rule Interactions in Accented Speech Synthesis
von: Lertpetchpun, Thanathai, et al.
Veröffentlicht: (2026)

DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers
von: Langedijk, Anna, et al.
Veröffentlicht: (2023)

Transformer See, Transformer Do: Copying as an Intermediate Step in Learning Analogical Reasoning
von: Hellwig, Philipp, et al.
Veröffentlicht: (2026)

Learning-free L2-Accented Speech Generation using Phonological Rules
von: Lertpetchpun, Thanathai, et al.
Veröffentlicht: (2026)

Multi-Level Embedding Conformer Framework for Bengali Automatic Speech Recognition
von: Sakib, Md. Nazmus, et al.
Veröffentlicht: (2025)

PhonologyBench: Evaluating Phonological Skills of Large Language Models
von: Suvarna, Ashima, et al.
Veröffentlicht: (2024)

[b]=[d]-[t]+[p]: Self-supervised Speech Models Discover Phonological Vector Arithmetic
von: Choi, Kwanghee, et al.
Veröffentlicht: (2026)

Remembering Unequally: Global and Disciplinary Bias in LLM Reconstruction of Scholarly Coauthor Lists
von: Kalhor, Ghazal, et al.
Veröffentlicht: (2025)

Assessing GPT's Bias Towards Stigmatized Social Groups: An Intersectional Case Study on Nationality Prejudice and Psychophobia
von: Kashif, Afifah, et al.
Veröffentlicht: (2025)

Semantic, Orthographic, and Phonological Biases in Humans' Wordle Gameplay
von: Liang, Jiadong, et al.
Veröffentlicht: (2024)

Cross-Linguistic Transcription and Phonological Representation in the Huìtóngguǎnxì Huáyíyìyǔ
von: Kim, Ji-eun
Veröffentlicht: (2026)

End-to-end Automatic Speech Recognition and Speech Translation: Integration of Speech Foundational Models and LLMs
von: Luu, Nam, et al.
Veröffentlicht: (2025)

The Role of $n$-gram Smoothing in the Age of Neural Networks
von: Malagutti, Luca, et al.
Veröffentlicht: (2024)

PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs
von: van der Wal, Oskar, et al.
Veröffentlicht: (2025)

How Tokenization Limits Phonological Knowledge Representation in Language Models and How to Improve Them
von: Liao, Disen, et al.
Veröffentlicht: (2026)

HATS: An Open data set Integrating Human Perception Applied to the Evaluation of Automatic Speech Recognition Metrics
von: Roux, Thibault Bañeras, et al.
Veröffentlicht: (2026)