Cover Image

Unsupervised lexicon learning from speech is limited by representations rather than clustering

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Slabbert, Danel, Malan, Simon, Kamper, Herman
Format:	Preprint
Published:	2025
Subjects:	Audio and Speech Processing Computation and Language Sound
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Revisiting speech segmentation and lexicon learning with better features
by: Kamper, Herman, et al.
Published: (2024)

ZeroSyl: Simple Zero-Resource Syllable Tokenization for Spoken Language Modeling
by: Visser, Nicol, et al.
Published: (2026)

Should Top-Down Clustering Affect Boundaries in Unsupervised Word Discovery?
by: Malan, Simon, et al.
Published: (2025)

Unsupervised Word Discovery: Boundary Detection with Clustering vs. Dynamic Programming
by: Malan, Simon, et al.
Published: (2024)

Translating speech with just images
by: Oneata, Dan, et al.
Published: (2024)

Data-driven grapheme-to-phoneme representations for a lexicon-free text-to-speech
by: Garg, Abhinav, et al.
Published: (2024)

Disentanglement in a GAN for Unconditional Speech Synthesis
by: Baas, Matthew, et al.
Published: (2023)

SpeechCLIP+: Self-supervised multi-task representation learning for speech via CLIP and speech-image data
by: Wang, Hsuan-Fu, et al.
Published: (2024)

Semantic enrichment towards efficient speech representations
by: Laperrière, Gaëlle, et al.
Published: (2023)

Speech Recognition for Automatically Assessing Afrikaans and isiXhosa Preschool Oral Narratives
by: Jacobs, Christiaan, et al.
Published: (2025)

A predictive learning model can simulate temporal dynamics and context effects found in neural representations of continuous speech
by: Liu, Oli Danyi, et al.
Published: (2024)

Can Whisper perform speech-based in-context learning?
by: Wang, Siyin, et al.
Published: (2023)

Self-supervised learning of speech representations with Dutch archival data
by: Vaessen, Nik, et al.
Published: (2025)

AfriHuBERT: A self-supervised speech representation model for African languages
by: Alabi, Jesujoba O., et al.
Published: (2024)

Target word activity detector: An approach to obtain ASR word boundaries without lexicon
by: Sivasankaran, Sunit, et al.
Published: (2024)

emg2speech: Synthesizing speech from electromyography using self-supervised speech models
by: Gowda, Harshavardhana T., et al.
Published: (2025)

Natural language guidance of high-fidelity text-to-speech with synthetic annotations
by: Lyth, Dan, et al.
Published: (2024)

Exploring the limits of decoder-only models trained on public speech recognition corpora
by: Gupta, Ankit, et al.
Published: (2024)

Can we reconstruct a dysarthric voice with the large speech model Parler TTS?
by: Sanchez, Ariadna, et al.
Published: (2025)

Improving child speech recognition with augmented child-like speech
by: Zhang, Yuanyuan, et al.
Published: (2024)

A low latency attention module for streaming self-supervised speech representation learning
by: Ma, Jianbo, et al.
Published: (2023)

Can large audio language models understand child stuttering speech? speech summarization, and source separation
by: Okocha, Chibuzor, et al.
Published: (2025)

The mutual exclusivity bias of bilingual visually grounded speech models
by: Oneata, Dan, et al.
Published: (2025)

A dual task learning approach to fine-tune a multilingual semantic speech encoder for Spoken Language Understanding
by: Laperrière, Gaëlle, et al.
Published: (2024)

Automated speech audiometry: Can it work using open-source pre-trained Kaldi-NL automatic speech recognition?
by: Araiza-Illan, Gloria, et al.
Published: (2023)

Noise-robust zero-shot text-to-speech synthesis conditioned on self-supervised speech-representation model with adapters
by: Fujita, Kenichi, et al.
Published: (2024)

LLM-based phoneme-to-grapheme for phoneme-based speech recognition
by: Ma, Te, et al.
Published: (2025)

Advancing LLM-based phoneme-to-grapheme for multilingual speech recognition
by: Dong, Lukuang, et al.
Published: (2026)

Self-consistent context aware conformer transducer for speech recognition
by: Kolokolov, Konstantin, et al.
Published: (2024)

An efficient text augmentation approach for contextualized Mandarin speech recognition
by: Zheng, Naijun, et al.
Published: (2024)

Direct Punjabi to English speech translation using discrete units
by: Kaur, Prabhjot, et al.
Published: (2024)

Transferable speech-to-text large language model alignment module
by: Wu, Boyong, et al.
Published: (2024)

Analyzing and Improving Speaker Similarity Assessment for Speech Synthesis
by: Carbonneau, Marc-André, et al.
Published: (2025)

Transferring speech-generic and depression-specific knowledge for Alzheimer's disease detection
by: Cui, Ziyun, et al.
Published: (2023)

Beyond the binary: Limitations and possibilities of gender-related speech technology research
by: Sanchez, Ariadna, et al.
Published: (2024)

An experiment on an automated literature survey of data-driven speech enhancement methods
by: Santos, Arthur dos, et al.
Published: (2023)

Convoifilter: A case study of doing cocktail party speech recognition
by: Nguyen, Thai-Binh, et al.
Published: (2023)

asr_eval: Algorithms and tools for multi-reference and streaming speech recognition evaluation
by: Sedukhin, Oleg, et al.
Published: (2026)

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

Neighbors and relatives: How do speech embeddings reflect linguistic connections across the world?
by: Törö, Tuukka, et al.
Published: (2025)