Cover Image

Self-Supervised Speech Representations are More Phonetic than Semantic

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Choi, Kwanghee, Pasad, Ankita, Nakamura, Tomohiko, Fukayama, Satoru, Livescu, Karen, Watanabe, Shinji
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Machine Learning Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

What Do Self-Supervised Speech Models Know About Words?
by: Pasad, Ankita, et al.
Published: (2023)

Discrete Speech Unit Extraction via Independent Component Analysis
by: Nakamura, Tomohiko, et al.
Published: (2025)

What do Speech Foundation Models Learn? Analysis and Applications
by: Pasad, Ankita
Published: (2025)

On the Effects of Heterogeneous Data Sources on Speech-to-Text Foundation Models
by: Tian, Jinchuan, et al.
Published: (2024)

Leveraging Allophony in Self-Supervised Speech Models for Atypical Pronunciation Assessment
by: Choi, Kwanghee, et al.
Published: (2025)

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

POWSM: A Phonetic Open Whisper-Style Speech Foundation Model
by: Li, Chin-Jou, et al.
Published: (2025)

DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding
by: Shon, Suwon, et al.
Published: (2024)

On-device Streaming Discrete Speech Units
by: Choi, Kwanghee, et al.
Published: (2025)

On the Evaluation of Speech Foundation Models for Spoken Language Understanding
by: Arora, Siddhant, et al.
Published: (2024)

JaCappella Corpus: A Japanese a Cappella Vocal Ensemble Corpus
by: Nakamura, Tomohiko, et al.
Published: (2022)

OpenBEATs: A Fully Open-Source General-Purpose Audio Encoder
by: Bharadwaj, Shikhar, et al.
Published: (2025)

The CMU-AIST submission for the ICME 2025 Audio Encoder Challenge
by: Bharadwaj, Shikhar, et al.
Published: (2026)

Benchmarking Prosody Encoding in Discrete Speech Tokens
by: Onda, Kentaro, et al.
Published: (2025)

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

FruitsMusic: A Real-World Corpus of Japanese Idol-Group Songs
by: Suda, Hitoshi, et al.
Published: (2024)

Speech Codec Probing from Semantic and Phonetic Perspectives
by: Shi, Xuan, et al.
Published: (2026)

IdolSongsJp Corpus: A Multi-Singer Song Corpus in the Style of Japanese Idol Groups
by: Suda, Hitoshi, et al.
Published: (2025)

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

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

Towards Robust Speech Representation Learning for Thousands of Languages
by: Chen, William, et al.
Published: (2024)

Voice Conversion for Likability Control via Automated Rating of Speech Synthesis Corpora
by: Suda, Hitoshi, et al.
Published: (2025)

AV2Wav: Diffusion-Based Re-synthesis from Continuous Self-supervised Features for Audio-Visual Speech Enhancement
by: Chou, Ju-Chieh, et al.
Published: (2023)

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

An Empirical Recipe for Universal Phone Recognition
by: Bharadwaj, Shikhar, et al.
Published: (2026)

Adapting Self-Supervised Speech Representations for Cross-lingual Dysarthria Detection in Parkinson's Disease
by: Hernandez, Abner, et al.
Published: (2026)

CTC-DRO: Robust Optimization for Reducing Language Disparities in Speech Recognition
by: Bartelds, Martijn, et al.
Published: (2025)

Enhancing the Stability of LLM-based Speech Generation Systems through Self-Supervised Representations
by: Martín-Cortinas, Álvaro, et al.
Published: (2024)

Training and Inference Efficiency of Encoder-Decoder Speech Models
by: Żelasko, Piotr, et al.
Published: (2025)

OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer
by: Peng, Yifan, et al.
Published: (2024)

Whistle: Data-Efficient Multilingual and Crosslingual Speech Recognition via Weakly Phonetic Supervision
by: Yusuyin, Saierdaer, et al.
Published: (2024)

SSVD-O: Parameter-Efficient Fine-Tuning with Structured SVD for Speech Recognition
by: Wang, Pu, et al.
Published: (2026)

MoshiRAG: Asynchronous Knowledge Retrieval for Full-Duplex Speech Language Models
by: Chien, Chung-Ming, et al.
Published: (2026)

Codec2Vec: Self-Supervised Speech Representation Learning Using Neural Speech Codecs
by: Tseng, Wei-Cheng, et al.
Published: (2025)

Discrete Tokens Exhibit Interlanguage Speech Intelligibility Benefit: an Analytical Study Towards Accent-robust ASR Only with Native Speech Data
by: Onda, Kentaro, et al.
Published: (2025)

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

ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, and Datasets
by: Shi, Jiatong, et al.
Published: (2024)

Phonetic Enhanced Language Modeling for Text-to-Speech Synthesis
by: Zhou, Kun, et al.
Published: (2024)

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

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