4 citations · 9 across the 11 of their papers we have counts for
11 papers
Speech Quality Embeddings for Improved Detection and Classification of Degradations in Speech Signals
Michael Kuhlmann, Tobias Cord-Landwehr, Reinhold Haeb-Umbach
Automatic subjective speech quality assessment (SSQA) traditionally estimates speech quality on an utterance or system level. While this resolution was adequate for older transmiss…
Speech Quality-Based Localization of Low-Quality Speech and Text-to-Speech Synthesis Artefacts
Michael Kuhlmann, Alexander Werning, Thilo von Neumann +1
A large number of works view the automatic assessment of speech from an utterance- or system-level perspective. While such approaches are good in judging overall quality, they cann…
Synthesizing speech with selected perceptual voice qualities - A case study with creaky voice
Frederik Rautenberg, Fritz Seebauer, Jana Wiechmann +3
The control of perceptual voice qualities in a text-to-speech (TTS) system is of interest for applications where unmanipu- lated and manipulated speech probes can serve to illustra…
Towards Frame-level Quality Predictions of Synthetic Speech
Michael Kuhlmann, Fritz Seebauer, Petra Wagner +1
While automatic subjective speech quality assessment has witnessed much progress, an open question is whether an automatic quality assessment at frame resolution is possible. This…
Speech Synthesis along Perceptual Voice Quality Dimensions
Frederik Rautenberg, Michael Kuhlmann, Fritz Seebauer +3
While expressive speech synthesis or voice conversion systems mainly focus on controlling or manipulating abstract prosodic characteristics of speech, such as emotion or accent, we…
Speaker and Style Disentanglement of Speech Based on Contrastive Predictive Coding Supported Factorized Variational Autoencoder
Yuying Xie, Michael Kuhlmann, Frederik Rautenberg +2
Speech signals encompass various information across multiple levels including content, speaker, and style. Disentanglement of these information, although challenging, is important…
LoFT: Local Proxy Fine-tuning For Improving Transferability Of Adversarial Attacks Against Large Language Model
Muhammad Ahmed Shah, Roshan Sharma, Hira Dhamyal +10
It has been shown that Large Language Model (LLM) alignments can be circumvented by appending specially crafted attack suffixes with harmful queries to elicit harmful responses. To…
On Feature Importance and Interpretability of Speaker Representations
Frederik Rautenberg, Michael Kuhlmann, Jana Wiechmann +3
Unsupervised speech disentanglement aims at separating fast varying from slowly varying components of a speech signal. In this contribution, we take a closer look at the embedding…
Investigating Speaker Embedding Disentanglement on Natural Read Speech
Michael Kuhlmann, Adrian Meise, Fritz Seebauer +2
Disentanglement is the task of learning representations that identify and separate factors that explain the variation observed in data. Disentangled representations are useful to i…
Investigation into Target Speaking Rate Adaptation for Voice Conversion
Michael Kuhlmann, Fritz Seebauer, Janek Ebbers +2
Disentangling speaker and content attributes of a speech signal into separate latent representations followed by decoding the content with an exchanged speaker representation is a…
Contrastive Predictive Coding Supported Factorized Variational Autoencoder for Unsupervised Learning of Disentangled Speech Representations
Janek Ebbers, Michael Kuhlmann, Tobias Cord-Landwehr +1
In this work we address disentanglement of style and content in speech signals. We propose a fully convolutional variational autoencoder employing two encoders: a content encoder a…