Buchumschlag

Can you Remove the Downstream Model for Speaker Recognition with Self-Supervised Speech Features?

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Aldeneh, Zakaria, Higuchi, Takuya, Jung, Jee-weon, Seto, Skyler, Likhomanenko, Tatiana, Shum, Stephen, Abdelaziz, Ahmed Hussen, Watanabe, Shinji, Theobald, Barry-John
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Sound Audio and Speech Processing
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Speaker-IPL: Unsupervised Learning of Speaker Characteristics with i-Vector based Pseudo-Labels
von: Aldeneh, Zakaria, et al.
Veröffentlicht: (2024)

Which Data Matter? Embedding-Based Data Selection for Speech Recognition
von: Aldeneh, Zakaria, et al.
Veröffentlicht: (2026)

Towards Automatic Assessment of Self-Supervised Speech Models using Rank
von: Aldeneh, Zakaria, et al.
Veröffentlicht: (2024)

ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf models
von: Jung, Jee-weon, et al.
Veröffentlicht: (2024)

Exploring Prediction Targets in Masked Pre-Training for Speech Foundation Models
von: Chen, Li-Wei, et al.
Veröffentlicht: (2024)

DiceHuBERT: Distilling HuBERT with a Self-Supervised Learning Objective
von: Chi, Hyung Gun, et al.
Veröffentlicht: (2025)

A Variational Framework for Improving Naturalness in Generative Spoken Language Models
von: Chen, Li-Wei, et al.
Veröffentlicht: (2025)

Closing the Gap Between Text and Speech Understanding in LLMs
von: Cuervo, Santiago, et al.
Veröffentlicht: (2025)

Learning Spatially-Aware Language and Audio Embeddings
von: Devnani, Bhavika, et al.
Veröffentlicht: (2024)

dMel: Speech Tokenization made Simple
von: Bai, Richard He, et al.
Veröffentlicht: (2024)

Improving Design of Input Condition Invariant Speech Enhancement
von: Zhang, Wangyou, et al.
Veröffentlicht: (2024)

Mechanisms of Multimodal Synchronization: Insights from Decoder-Based Video-Text-to-Speech Synthesis
von: Gupta, Akshita, et al.
Veröffentlicht: (2024)

Beyond Performance Plateaus: A Comprehensive Study on Scalability in Speech Enhancement
von: Zhang, Wangyou, et al.
Veröffentlicht: (2024)

Disentangled Representation Learning for Environment-agnostic Speaker Recognition
von: Nam, KiHyun, et al.
Veröffentlicht: (2024)

Omni-Router: Sharing Routing Decisions in Sparse Mixture-of-Experts for Speech Recognition
von: Gu, Zijin, et al.
Veröffentlicht: (2025)

Speech Foundation Models Generalize to Time Series Tasks from Wearable Sensor Data
von: Narain, Jaya, et al.
Veröffentlicht: (2025)

End-to-End Speech Recognition with Pre-trained Masked Language Model
von: Higuchi, Yosuke, et al.
Veröffentlicht: (2024)

Leveraging Audio-Visual Data to Reduce the Multilingual Gap in Self-Supervised Speech Models
von: Blandón, María Andrea Cruz, et al.
Veröffentlicht: (2025)

AugSumm: towards generalizable speech summarization using synthetic labels from large language model
von: Jung, Jee-weon, et al.
Veröffentlicht: (2024)

ExpertLens: Activation steering features are highly interpretable
von: Fedzechkina, Masha, et al.
Veröffentlicht: (2025)

Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions in Multilingual Language Models
von: Sundar, Anirudh, et al.
Veröffentlicht: (2025)

The VoxCeleb Speaker Recognition Challenge: A Retrospective
von: Huh, Jaesung, et al.
Veröffentlicht: (2024)

Hypothesis Clustering and Merging: Novel MultiTalker Speech Recognition with Speaker Tokens
von: Kashiwagi, Yosuke, et al.
Veröffentlicht: (2024)

Beyond Silence: Bias Analysis through Loss and Asymmetric Approach in Audio Anti-Spoofing
von: Shim, Hye-jin, et al.
Veröffentlicht: (2024)

Improving Audio Captioning Models with Fine-grained Audio Features, Text Embedding Supervision, and LLM Mix-up Augmentation
von: Wu, Shih-Lun, et al.
Veröffentlicht: (2023)

Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation tasks
von: Maiti, Soumi, et al.
Veröffentlicht: (2023)

Aggregate-and-Adapt Natural Language Prompts for Downstream Generalization of CLIP
von: Huang, Chen, et al.
Veröffentlicht: (2024)

TMT: Tri-Modal Translation between Speech, Image, and Text by Processing Different Modalities as Different Languages
von: Kim, Minsu, et al.
Veröffentlicht: (2024)

Does Single-channel Speech Enhancement Improve Keyword Spotting Accuracy? A Case Study
von: Brueggeman, Avamarie, et al.
Veröffentlicht: (2023)

ChipChat: Low-Latency Cascaded Conversational Agent in MLX
von: Likhomanenko, Tatiana, et al.
Veröffentlicht: (2025)

Context-Driven Dynamic Pruning for Large Speech Foundation Models
von: Someki, Masao, et al.
Veröffentlicht: (2025)

Two-level adiabatic transition probability for small avoided crossings generated by tangential intersections
von: Higuchi, Kenta, et al.
Veröffentlicht: (2024)

Neural Blind Source Separation and Diarization for Distant Speech Recognition
von: Bando, Yoshiaki, et al.
Veröffentlicht: (2024)

SpeakStream: Streaming Text-to-Speech with Interleaved Data
von: Bai, Richard He, et al.
Veröffentlicht: (2025)

Multichannel Voice Trigger Detection Based on Transform-average-concatenate
von: Higuchi, Takuya, et al.
Veröffentlicht: (2023)

Generating Data with Text-to-Speech and Large-Language Models for Conversational Speech Recognition
von: Cornell, Samuele, et al.
Veröffentlicht: (2024)

Useful Blunders: Can Automated Speech Recognition Errors Improve Downstream Dementia Classification?
von: Li, Changye, et al.
Veröffentlicht: (2024)

SEED: Speaker Embedding Enhancement Diffusion Model
von: Nam, KiHyun, et al.
Veröffentlicht: (2025)

Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting
von: Huang, Chen, et al.
Veröffentlicht: (2025)

Chain-of-Thought Training for Open E2E Spoken Dialogue Systems
von: Arora, Siddhant, et al.
Veröffentlicht: (2025)