Image de couverture de livre

Revisiting speech segmentation and lexicon learning with better features

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kamper, Herman, van Niekerk, Benjamin
Format:	Preprint
Publié:	2024
Sujets:	Audio and Speech Processing Computation and Language Sound
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Unsupervised lexicon learning from speech is limited by representations rather than clustering
par: Slabbert, Danel, et autres
Publié: (2025)

Unsupervised Word Discovery: Boundary Detection with Clustering vs. Dynamic Programming
par: Malan, Simon, et autres
Publié: (2024)

Should Top-Down Clustering Affect Boundaries in Unsupervised Word Discovery?
par: Malan, Simon, et autres
Publié: (2025)

Translating speech with just images
par: Oneata, Dan, et autres
Publié: (2024)

Disentanglement in a GAN for Unconditional Speech Synthesis
par: Baas, Matthew, et autres
Publié: (2023)

Data-driven grapheme-to-phoneme representations for a lexicon-free text-to-speech
par: Garg, Abhinav, et autres
Publié: (2024)

Analyzing and Improving Speaker Similarity Assessment for Speech Synthesis
par: Carbonneau, Marc-André, et autres
Publié: (2025)

LinearVC: Linear transformations of self-supervised features through the lens of voice conversion
par: Kamper, Herman, et autres
Publié: (2025)

Interpreting Speaker Characteristics in the Dimensions of Self-Supervised Speech Features
par: van Rensburg, Kyle Janse, et autres
Publié: (2026)

Forensic deepfake audio detection using segmental speech features
par: Yang, Tianle, et autres
Publié: (2025)

Speech Recognition for Automatically Assessing Afrikaans and isiXhosa Preschool Oral Narratives
par: Jacobs, Christiaan, et autres
Publié: (2025)

Can Whisper perform speech-based in-context learning?
par: Wang, Siyin, et autres
Publié: (2023)

SpeechCLIP+: Self-supervised multi-task representation learning for speech via CLIP and speech-image data
par: Wang, Hsuan-Fu, et autres
Publié: (2024)

Target word activity detector: An approach to obtain ASR word boundaries without lexicon
par: Sivasankaran, Sunit, et autres
Publié: (2024)

emg2speech: Synthesizing speech from electromyography using self-supervised speech models
par: Gowda, Harshavardhana T., et autres
Publié: (2025)

Improving child speech recognition with augmented child-like speech
par: Zhang, Yuanyuan, et autres
Publié: (2024)

Self-supervised learning of speech representations with Dutch archival data
par: Vaessen, Nik, et autres
Publié: (2025)

Can large audio language models understand child stuttering speech? speech summarization, and source separation
par: Okocha, Chibuzor, et autres
Publié: (2025)

The mutual exclusivity bias of bilingual visually grounded speech models
par: Oneata, Dan, et autres
Publié: (2025)

A dual task learning approach to fine-tune a multilingual semantic speech encoder for Spoken Language Understanding
par: Laperrière, Gaëlle, et autres
Publié: (2024)

A predictive learning model can simulate temporal dynamics and context effects found in neural representations of continuous speech
par: Liu, Oli Danyi, et autres
Publié: (2024)

Automated speech audiometry: Can it work using open-source pre-trained Kaldi-NL automatic speech recognition?
par: Araiza-Illan, Gloria, et autres
Publié: (2023)

Semantic enrichment towards efficient speech representations
par: Laperrière, Gaëlle, et autres
Publié: (2023)

Self-consistent context aware conformer transducer for speech recognition
par: Kolokolov, Konstantin, et autres
Publié: (2024)

An efficient text augmentation approach for contextualized Mandarin speech recognition
par: Zheng, Naijun, et autres
Publié: (2024)

Direct Punjabi to English speech translation using discrete units
par: Kaur, Prabhjot, et autres
Publié: (2024)

Transferable speech-to-text large language model alignment module
par: Wu, Boyong, et autres
Publié: (2024)

Advancing LLM-based phoneme-to-grapheme for multilingual speech recognition
par: Dong, Lukuang, et autres
Publié: (2026)

LLM-based phoneme-to-grapheme for phoneme-based speech recognition
par: Ma, Te, et autres
Publié: (2025)

Natural language guidance of high-fidelity text-to-speech with synthetic annotations
par: Lyth, Dan, et autres
Publié: (2024)

Beyond the binary: Limitations and possibilities of gender-related speech technology research
par: Sanchez, Ariadna, et autres
Publié: (2024)

Transferring speech-generic and depression-specific knowledge for Alzheimer's disease detection
par: Cui, Ziyun, et autres
Publié: (2023)

An experiment on an automated literature survey of data-driven speech enhancement methods
par: Santos, Arthur dos, et autres
Publié: (2023)

Convoifilter: A case study of doing cocktail party speech recognition
par: Nguyen, Thai-Binh, et autres
Publié: (2023)

Exploring the limits of decoder-only models trained on public speech recognition corpora
par: Gupta, Ankit, et autres
Publié: (2024)

asr_eval: Algorithms and tools for multi-reference and streaming speech recognition evaluation
par: Sedukhin, Oleg, et autres
Publié: (2026)

Linguists should learn to love speech-based deep learning models
par: Kloots, Marianne de Heer, et autres
Publié: (2025)

Automatic speech recognition for the Nepali language using CNN, bidirectional LSTM and ResNet
par: Dhakal, Manish, et autres
Publié: (2024)

AfriHuBERT: A self-supervised speech representation model for African languages
par: Alabi, Jesujoba O., et autres
Publié: (2024)

Korean aegyo speech shows systematic F1 increase to signal childlike qualities
par: Kim, Ji-eun, et autres
Publié: (2026)