Sparse Autoencoder Insights on Voice Embeddings

• URL: http://arxiv.org/abs/2502.00127v1
• Date: Fri, 31 Jan 2025 19:21:43 GMT
• Title: Sparse Autoencoder Insights on Voice Embeddings
• Authors: Daniel Pluth, Yu Zhou, Vijay K. Gurbani,
• Abstract summary: This study applies sparse autoencoders to speaker embeddings generated from a Titanet model. The extracted features exhibit characteristics similar to those found in Large Language Model embeddings, including feature splitting and steering. The analysis reveals that the autoencoder can identify and manipulate features such as language and music, which are not evident in the original embedding.
• Score: 3.2377830280631468
• License:
• Abstract: Recent advances in explainable machine learning have highlighted the potential of sparse autoencoders in uncovering mono-semantic features in densely encoded embeddings. While most research has focused on Large Language Model (LLM) embeddings, the applicability of this technique to other domains remains largely unexplored. This study applies sparse autoencoders to speaker embeddings generated from a Titanet model, demonstrating the effectiveness of this technique in extracting mono-semantic features from non-textual embedded data. The results show that the extracted features exhibit characteristics similar to those found in LLM embeddings, including feature splitting and steering. The analysis reveals that the autoencoder can identify and manipulate features such as language and music, which are not evident in the original embedding. The findings suggest that sparse autoencoders can be a valuable tool for understanding and interpreting embedded data in many domains, including audio-based speaker recognition.

Related papers

• The Complexity of Learning Sparse Superposed Features with Feedback [0.9838799448847586]
  We investigate whether the underlying learned features of a model can be efficiently retrieved through feedback from an agent. We analyze the feedback complexity associated with learning a feature matrix in sparse settings. Our results establish tight bounds when the agent is permitted to construct activations and demonstrate strong upper bounds in sparse scenarios.
  arXiv  Detail & Related papers  (2025-02-08T01:54:23Z)
• Disentangling Dense Embeddings with Sparse Autoencoders [0.0]
  Sparse autoencoders (SAEs) have shown promise in extracting interpretable features from complex neural networks. We present one of the first applications of SAEs to dense text embeddings from large language models. We show that the resulting sparse representations maintain semantic fidelity while offering interpretability.
  arXiv  Detail & Related papers  (2024-08-01T15:46:22Z)
• Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models [55.19497659895122]
  We introduce methods for discovering and applying sparse feature circuits. These are causally implicatedworks of human-interpretable features for explaining language model behaviors.
  arXiv  Detail & Related papers  (2024-03-28T17:56:07Z)
• Tram: A Token-level Retrieval-augmented Mechanism for Source Code Summarization [76.57699934689468]
  We propose a fine-grained Token-level retrieval-augmented mechanism (Tram) on the decoder side to enhance the performance of neural models. To overcome the challenge of token-level retrieval in capturing contextual code semantics, we also propose integrating code semantics into individual summary tokens.
  arXiv  Detail & Related papers  (2023-05-18T16:02:04Z)
• Introducing Semantics into Speech Encoders [91.37001512418111]
  We propose an unsupervised way of incorporating semantic information from large language models into self-supervised speech encoders without labeled audio transcriptions. Our approach achieves similar performance as supervised methods trained on over 100 hours of labeled audio transcripts.
  arXiv  Detail & Related papers  (2022-11-15T18:44:28Z)
• Deep Neural Convolutive Matrix Factorization for Articulatory Representation Decomposition [48.56414496900755]
  This work uses a neural implementation of convolutive sparse matrix factorization to decompose the articulatory data into interpretable gestures and gestural scores. Phoneme recognition experiments were additionally performed to show that gestural scores indeed code phonological information successfully.
  arXiv  Detail & Related papers  (2022-04-01T14:25:19Z)
• Preliminary study on using vector quantization latent spaces for TTS/VC systems with consistent performance [55.10864476206503]
  We investigate the use of quantized vectors to model the latent linguistic embedding. By enforcing different policies over the latent spaces in the training, we are able to obtain a latent linguistic embedding. Our experiments show that the voice cloning system built with vector quantization has only a small degradation in terms of perceptive evaluations.
  arXiv  Detail & Related papers  (2021-06-25T07:51:35Z)
• A comprehensive empirical analysis on cross-domain semantic enrichment for detection of depressive language [0.9749560288448115]
  We start with a rich word embedding pre-trained from a large general dataset, which is then augmented with embeddings learned from a much smaller and more specific domain dataset through a simple non-linear mapping mechanism. We show that our augmented word embedding representations achieve a significantly better F1 score than the others, specially when applied to a high quality dataset.
  arXiv  Detail & Related papers  (2021-06-24T07:15:09Z)
• Unsupervised Pattern Discovery from Thematic Speech Archives Based on Multilingual Bottleneck Features [41.951988293049205]
  We propose a two-stage approach, which comprises unsupervised acoustic modeling and decoding, followed by pattern mining in acoustic unit sequences. The proposed system is able to effectively extract topic-related words and phrases from the lecture recordings on MIT OpenCourseWare.
  arXiv  Detail & Related papers  (2020-11-03T20:06:48Z)
• Intrinsic Probing through Dimension Selection [69.52439198455438]
  Most modern NLP systems make use of pre-trained contextual representations that attain astonishingly high performance on a variety of tasks. Such high performance should not be possible unless some form of linguistic structure inheres in these representations, and a wealth of research has sprung up on probing for it. In this paper, we draw a distinction between intrinsic probing, which examines how linguistic information is structured within a representation, and the extrinsic probing popular in prior work, which only argues for the presence of such information by showing that it can be successfully extracted.
  arXiv  Detail & Related papers  (2020-10-06T15:21:08Z)
• Feature Learning for Accelerometer based Gait Recognition [0.0]
  Autoencoders are very close to discriminative end-to-end models with regards to their feature learning ability. fully convolutional models are able to learn good feature representations, regardless of the training strategy.
  arXiv  Detail & Related papers  (2020-07-31T10:58:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.