Related papers: New Challenges for Content Privacy in Speech and A…
Mobile Large Language Models (LLMs) are revolutionizing diverse fields such as healthcare, finance, and education with their ability to perform advanced natural language processing tasks on-the-go. However, the deployment of these models in…
Speech summarization has become an essential tool for efficiently managing and accessing the growing volume of spoken and audiovisual content. However, despite its increasing importance, speech summarization remains loosely defined. The…
Text-to-Speech (TTS) and Voice Conversion (VC) models have exhibited remarkable performance in generating realistic and natural audio. However, their dark side, audio deepfake poses a significant threat to both society and individuals.…
Large Language Models (LLMs) represent a significant advancement in artificial intelligence, finding applications across various domains. However, their reliance on massive internet-sourced datasets for training brings notable privacy…
Automated audio captioning is a cross-modal translation task that aims to generate natural language descriptions for given audio clips. This task has received increasing attention with the release of freely available datasets in recent…
Recordings in everyday life require privacy preservation of the speech content and speaker identity. This contribution explores the influence of noise and reverberation on the trade-off between privacy and utility for low-cost…
The performance of a voice anonymization system is typically measured according to its ability to hide the speaker's identity and keep the data's utility for downstream tasks. This means that the requirements the anonymization should…
Voice anonymisation can be used to help protect speaker privacy when speech data is shared with untrusted others. In most practical applications, while the voice identity should be sanitised, other attributes such as the spoken content…
Privacy policies are the main way to obtain information related to personal data collection and processing. Originally, privacy policies were presented as textual documents. However, the unsuitability of this format for the needs of today's…
While the study of language as typed on smartphones offers valuable insights, existing data collection methods often fall short in providing contextual information and ensuring user privacy. We present a privacy-respectful approach -…
In this paper the current status and open challenges of synthetic speech detection are addressed. The work comprises an initial analysis of available open datasets and of existing detection methods, a description of the requirements for new…
Massive developments in mobile wireless telecommunication networks have been made during the last few decades. At present, mobile users are getting familiar with the latest 5G networks, and the discussion for the next generation of Beyond…
The proliferation of speech technologies and rising privacy legislation calls for the development of privacy preservation solutions for speech applications. These are essential since speech signals convey a wealth of rich, personal and…
In the era of generative artificial intelligence and the Internet of Things, while there is explosive growth in the volume of data and the associated need for processing, analysis, and storage, several new challenges are faced in…
We identify a novel phenomenon in language models: benign fine-tuning of frontier models can lead to privacy collapse. We find that diverse, subtle patterns in training data can degrade contextual privacy, including optimisation for…
In ubiquitous computing domain context awareness is an important issue. So, in ubiquitous computing, mere protection of message confidentiality is not sufficient for most of the applications where context-awareness can lead to near…
In recent years, the need for privacy preservation when manipulating or storing personal data, including speech , has become a major issue. In this paper, we present a system addressing the speaker-level anonymization problem. We propose…
Fast development of sharing services has become a crucial part of the cyber-enabled world construction process, as sharing services reinvent how people exchange and obtain goods or services. However, privacy leakage or disclosure remains a…
Sharing real-world speech utterances is key to the training and deployment of voice-based services. However, it also raises privacy risks as speech contains a wealth of personal data. Speaker anonymization aims to remove speaker information…
Voice user interfaces and digital assistants are rapidly entering our lives and becoming singular touch points spanning our devices. These always-on services capture and transmit our audio data to powerful cloud services for further…