Cover Image

How Redundant Is the Transformer Stack in Speech Representation Models?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dorszewski, Teresa, Jacobsen, Albert Kjøller, Tětková, Lenka, Hansen, Lars Kai
Format:	Preprint
Published:	2024
Subjects:	Audio and Speech Processing Computation and Language Machine Learning Sound
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Convexity-based Pruning of Speech Representation Models
by: Dorszewski, Teresa, et al.
Published: (2024)

SpeechX: Neural Codec Language Model as a Versatile Speech Transformer
by: Wang, Xiaofei, et al.
Published: (2023)

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

Property Neurons in Self-Supervised Speech Transformers
by: Lin, Tzu-Quan, et al.
Published: (2024)

Understanding Self-Supervised Learning of Speech Representation via Invariance and Redundancy Reduction
by: Brima, Yusuf, et al.
Published: (2023)

Is Smaller Always Faster? Tradeoffs in Compressing Self-Supervised Speech Transformers
by: Lin, Tzu-Quan, et al.
Published: (2022)

Robust and Unbounded Length Generalization in Autoregressive Transformer-Based Text-to-Speech
by: Battenberg, Eric, et al.
Published: (2024)

CA-SSLR: Condition-Aware Self-Supervised Learning Representation for Generalized Speech Processing
by: Lu, Yen-Ju, et al.
Published: (2024)

Prosodic ABX: A Language-Agnostic Method for Measuring Prosodic Contrast in Speech Representations
by: Sun, Haitong, et al.
Published: (2026)

Modeling Overlapped Speech with Shuffles
by: Wiesner, Matthew, et al.
Published: (2026)

Textually Pretrained Speech Language Models
by: Hassid, Michael, et al.
Published: (2023)

On the Problem of Text-To-Speech Model Selection for Synthetic Data Generation in Automatic Speech Recognition
by: Rossenbach, Nick, et al.
Published: (2024)

Africa-Centric Self-Supervised Pre-Training for Multilingual Speech Representation in a Sub-Saharan Context
by: Caubrière, Antoine, et al.
Published: (2024)

Analyzing Speech Unit Selection for Textless Speech-to-Speech Translation
by: Duret, Jarod, et al.
Published: (2024)

Coupling Speech Encoders with Downstream Text Models
by: Chelba, Ciprian, et al.
Published: (2024)

Energy-Based Models with Applications to Speech and Language Processing
by: Ou, Zhijian
Published: (2024)

SimulTron: On-Device Simultaneous Speech to Speech Translation
by: Agranovich, Alex, et al.
Published: (2024)

Translatotron 3: Speech to Speech Translation with Monolingual Data
by: Nachmani, Eliya, et al.
Published: (2023)

OLMoASR: Open Models and Data for Training Robust Speech Recognition Models
by: Ngo, Huong, et al.
Published: (2025)

On the Semantic Latent Space of Diffusion-Based Text-to-Speech Models
by: Varshavsky-Hassid, Miri, et al.
Published: (2024)

Towards Early Prediction of Self-Supervised Speech Model Performance
by: Whetten, Ryan, et al.
Published: (2025)

Towards Robust FastSpeech 2 by Modelling Residual Multimodality
by: Kögel, Fabian, et al.
Published: (2023)

Speech Robust Bench: A Robustness Benchmark For Speech Recognition
by: Shah, Muhammad A., et al.
Published: (2024)

Investigating Disentanglement in a Phoneme-level Speech Codec for Prosody Modeling
by: Karapiperis, Sotirios, et al.
Published: (2024)

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions
by: Wagner, Dominik, et al.
Published: (2025)

Pre-Trained Foundation Model representations to uncover Breathing patterns in Speech
by: Mitra, Vikramjit, et al.
Published: (2024)

Universal Robust Speech Adaptation for Cross-Domain Speech Recognition and Enhancement
by: Wang, Chien-Chun, et al.
Published: (2026)

Speech Recognition With LLMs Adapted to Disordered Speech Using Reinforcement Learning
by: Nagpal, Chirag, et al.
Published: (2024)

ProMode: A Speech Prosody Model Conditioned on Acoustic and Textual Inputs
by: Eren, Eray, et al.
Published: (2025)

Efficient Training of Self-Supervised Speech Foundation Models on a Compute Budget
by: Liu, Andy T., et al.
Published: (2024)

DC-Spin: A Speaker-invariant Speech Tokenizer for Spoken Language Models
by: Chang, Heng-Jui, et al.
Published: (2024)

CoSTA: Code-Switched Speech Translation using Aligned Speech-Text Interleaving
by: Shankar, Bhavani, et al.
Published: (2024)

The ParlaSpeech Collection of Automatically Generated Speech and Text Datasets from Parliamentary Proceedings
by: Ljubešić, Nikola, et al.
Published: (2024)

Spontaneous Style Text-to-Speech Synthesis with Controllable Spontaneous Behaviors Based on Language Models
by: Li, Weiqin, et al.
Published: (2024)

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

In-Sync: Adaptation of Speech Aware Large Language Models for ASR with Word Level Timestamp Predictions
by: Fan, Xulin, et al.
Published: (2026)

Self-Supervised Speech Models Encode Phonetic Context via Position-dependent Orthogonal Subspaces
by: Choi, Kwanghee, et al.
Published: (2026)

TTSDS -- Text-to-Speech Distribution Score
by: Minixhofer, Christoph, et al.
Published: (2024)

PAST: Phonetic-Acoustic Speech Tokenizer
by: Har-Tuv, Nadav, et al.
Published: (2025)

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