Copertina

What Do Self-Supervised Speech and Speaker Models Learn? New Findings From a Cross Model Layer-Wise Analysis

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ashihara, Takanori, Delcroix, Marc, Moriya, Takafumi, Matsuura, Kohei, Asami, Taichi, Ijima, Yusuke
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language Sound Audio and Speech Processing
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

SpeechGLUE: How Well Can Self-Supervised Speech Models Capture Linguistic Knowledge?
di: Ashihara, Takanori, et al.
Pubblicazione: (2023)

Investigation of Speaker Representation for Target-Speaker Speech Processing
di: Ashihara, Takanori, et al.
Pubblicazione: (2024)

Boosting Hybrid Autoregressive Transducer-based ASR with Internal Acoustic Model Training and Dual Blank Thresholding
di: Moriya, Takafumi, et al.
Pubblicazione: (2024)

Guided Speaker Embedding
di: Horiguchi, Shota, et al.
Pubblicazione: (2024)

Recursive Attentive Pooling for Extracting Speaker Embeddings from Multi-Speaker Recordings
di: Horiguchi, Shota, et al.
Pubblicazione: (2024)

Generic Speech Enhancement with Self-Supervised Representation Space Loss
di: Sato, Hiroshi, et al.
Pubblicazione: (2025)

Frontend Token Enhancement for Token-Based Speech Recognition
di: Ashihara, Takanori, et al.
Pubblicazione: (2026)

Lightweight Zero-shot Text-to-Speech with Mixture of Adapters
di: Fujita, Kenichi, et al.
Pubblicazione: (2024)

Mitigating Non-Target Speaker Bias in Guided Speaker Embedding
di: Horiguchi, Shota, et al.
Pubblicazione: (2025)

Alignment-Free Training for Transducer-based Multi-Talker ASR
di: Moriya, Takafumi, et al.
Pubblicazione: (2024)

Can We Really Repurpose Multi-Speaker ASR Corpus for Speaker Diarization?
di: Horiguchi, Shota, et al.
Pubblicazione: (2025)

SpeakerBeam-SS: Real-time Target Speaker Extraction with Lightweight Conv-TasNet and State Space Modeling
di: Sato, Hiroshi, et al.
Pubblicazione: (2024)

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

TS-SUPERB: A Target Speech Processing Benchmark for Speech Self-Supervised Learning Models
di: Peng, Junyi, et al.
Pubblicazione: (2025)

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

Probing Self-supervised Learning Models with Target Speech Extraction
di: Peng, Junyi, et al.
Pubblicazione: (2024)

Pretraining Multi-Speaker Identification for Neural Speaker Diarization
di: Horiguchi, Shota, et al.
Pubblicazione: (2025)

Applying LLMs for Rescoring N-best ASR Hypotheses of Casual Conversations: Effects of Domain Adaptation and Context Carry-over
di: Ogawa, Atsunori, et al.
Pubblicazione: (2024)

Mamba-based Segmentation Model for Speaker Diarization
di: Plaquet, Alexis, et al.
Pubblicazione: (2024)

Joint Training of Speaker Embedding Extractor, Speech and Overlap Detection for Diarization
di: Pálka, Petr, et al.
Pubblicazione: (2024)

NTT Multi-Speaker ASR System for the DASR Task of CHiME-8 Challenge
di: Kamo, Naoyuki, et al.
Pubblicazione: (2024)

Target Speech Extraction with Pre-trained Self-supervised Learning Models
di: Peng, Junyi, et al.
Pubblicazione: (2024)

Speech Rhythm-Based Speaker Embeddings Extraction from Phonemes and Phoneme Duration for Multi-Speaker Speech Synthesis
di: Fujita, Kenichi, et al.
Pubblicazione: (2024)

Array Geometry-Robust Attention-Based Neural Beamformer for Moving Speakers
di: Tammen, Marvin, et al.
Pubblicazione: (2024)

Can you Remove the Downstream Model for Speaker Recognition with Self-Supervised Speech Features?
di: Aldeneh, Zakaria, et al.
Pubblicazione: (2024)

Evaluating Self-Supervised Speech Models via Text-Based LLMS
di: Maekaku, Takashi, et al.
Pubblicazione: (2025)

Rethinking Processing Distortions: Disentangling the Impact of Speech Enhancement Errors on Speech Recognition Performance
di: Ochiai, Tsubasa, et al.
Pubblicazione: (2024)

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers
di: Lin, Tzu-Quan, et al.
Pubblicazione: (2025)

Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization
di: von Neumann, Thilo, et al.
Pubblicazione: (2023)

Speaker Disentanglement of Speech Pre-trained Model Based on Interpretability
di: Zhu, Xiaoxu, et al.
Pubblicazione: (2025)

Enhanced Reverberation as Supervision for Unsupervised Speech Separation
di: Saijo, Kohei, et al.
Pubblicazione: (2024)

Vox-Profile: A Speech Foundation Model Benchmark for Characterizing Diverse Speaker and Speech Traits
di: Feng, Tiantian, et al.
Pubblicazione: (2025)

Resource-Efficient Adaptation of Speech Foundation Models for Multi-Speaker ASR
di: Wang, Weiqing, et al.
Pubblicazione: (2024)

MGFF-TDNN: A Multi-Granularity Feature Fusion TDNN Model with Depth-Wise Separable Module for Speaker Verification
di: Li, Ya, et al.
Pubblicazione: (2025)

Layer-Wise Analysis of Self-Supervised Acoustic Word Embeddings: A Study on Speech Emotion Recognition
di: Saliba, Alexandra, et al.
Pubblicazione: (2024)

A Large-Scale Probing Analysis of Speaker-Specific Attributes in Self-Supervised Speech Representations
di: Chiu, Aemon Yat Fei, et al.
Pubblicazione: (2025)

A Stage-Wise Learning Strategy with Fixed Anchors for Robust Speaker Verification
di: Gu, Bin, et al.
Pubblicazione: (2025)

What Do Speech Foundation Models Not Learn About Speech?
di: Waheed, Abdul, et al.
Pubblicazione: (2024)

Structured Speaker-Deficiency Adaptation of Foundation Models for Dysarthric and Elderly Speech Recognition
di: Hu, Shujie, et al.
Pubblicazione: (2024)

Enhancing Speaker-Independent Dysarthric Speech Severity Classification with DSSCNet and Cross-Corpus Adaptation
di: Roy, Arnab Kumar, et al.
Pubblicazione: (2025)