paper-with-me

Papers

Probing Speaker-specific Features in Speaker Representations

2025-01-09 · Aemon Yat Fei Chiu, Paco Kei Ching Fung, Roger Tsz Yeung Li, Jingyu Li, Tan Lee

This study explores speaker-specific features encoded in speaker embeddings and intermediate layers of speech self-supervised learning (SSL) models. By utilising a probing method, we analyse features such as pitch, tempo, and energy across prominent speaker embedding models and speech SSL models, including HuBERT, WavLM, and Wav2vec 2.0. The results reveal that speaker embeddings like CAM++ excel in energy classification, while speech SSL models demonstrate superior performance across multiple features due to their hierarchical feature encoding. Intermediate layers effectively capture a mix of acoustic and para-linguistic information, with deeper layers refining these representations. This investigation provides insights into model design and highlights the potential of these representations for downstream applications, such as speaker verification and text-to-speech synthesis, while laying the groundwork for exploring additional features and advanced probing methods.

📄 PDF Abstract BibTeX arXiv:2501.05310

Code (0)

등록된 구현이 없습니다.

Tasks

Self-Supervised LearningSpeaker VerificationSpeech Synthesistext-to-speechText to SpeechText-To-Speech Synthesis

Similar Papers 제목 키워드 기반

Analyzing Speaker Information in Self-Supervised Models to Improve Zero-Resource Speech Processing

2021-08-02 · Benjamin van Niekerk, Leanne Nortje, Matthew Baas, Herman Kamper

Contrastive predictive coding (CPC) aims to learn representations of speech by distinguishing future observations from a set of negative examples. Previous work has shown that linear classifiers trained on CPC features c…

Acoustic Unit DiscoveryLanguage ModelingLanguage ModellingSpeaker Verification

Beyond Decodability: Reconstructing Language Model Representations with an Encoding Probe

2026-05-01 · Gaofei Shen, Martijn Bentum, Tom Lentz, Afra Alishahi 외 arxiv

Probing is widely used to study which features can be decoded from language model representations. However, the common decoding probe approach has two limitations that we aim to solve with our new encoding probe approach…

Probing Deep Speaker Embeddings for Speaker-related Tasks

2022-12-14 · Zifeng Zhao, Ding Pan, Junyi Peng, Rongzhi Gu

Deep speaker embeddings have shown promising results in speaker recognition, as well as in other speaker-related tasks. However, some issues are still under explored, for instance, the information encoded in these repres…

Speaker RecognitionSpeaker Verificationtext-to-speechText to Speech

Audio ALBERT: A Lite BERT for Self-supervised Learning of Audio Representation

2020-05-18 · Po-Han Chi, Pei-Hung Chung, Tsung-Han Wu, Chun-Cheng Hsieh 외

For self-supervised speech processing, it is crucial to use pretrained models as speech representation extractors. In recent works, increasing the size of the model has been utilized in acoustic model training in order t…

Self-Supervised LearningSpeaker Identification

Self-supervised Predictive Coding Models Encode Speaker and Phonetic Information in Orthogonal Subspaces

2023-05-21 · Oli Liu, Hao Tang, Sharon Goldwater

Self-supervised speech representations are known to encode both speaker and phonetic information, but how they are distributed in the high-dimensional space remains largely unexplored. We hypothesize that they are encode…

Disentanglement