相关论文: Gender Bias in Instruction-Guided Speech Synthesis…

Recent advancements in speech synthesis have enabled large language model (LLM)-based systems to perform zero-shot generation with controllable content, timbre, speaker identity, and emotion through input prompts. As a result, these models…

Large language models (LLMs) are increasingly deployed in socially sensitive settings despite substantial documentation that they encode gender biases. Chain-of-Thought (CoT) prompting has been proposed as a bias-mitigation approach.…

Recent large-scale text-driven synthesis models have attracted much attention thanks to their remarkable capabilities of generating highly diverse images that follow given text prompts. Such text-based synthesis methods are particularly…

Machine translation (MT) systems often translate terms with ambiguous gender (e.g., English term "the nurse") into the gendered form that is most prevalent in the systems' training data (e.g., "enfermera", the Spanish term for a female…

Language models are susceptible to bias, sycophancy, backdoors, and other tendencies that lead to unfaithful responses to the input context. Interpreting internal states of language models could help monitor and correct unfaithful behavior.…

Speaker-adaptive Text-to-Speech (TTS) synthesis has attracted considerable attention due to its broad range of applications, such as personalized voice assistant services. While several approaches have been proposed, they often exhibit high…

Vast availability of text data has enabled widespread training and use of AI systems that not only learn and predict attributes from the text but also generate text automatically. However, these AI models also learn gender, racial and…

In emergency medicine, timely intervention for patients at risk of suicide is often hindered by delayed access to specialised psychiatric care. To bridge this gap, we introduce a speech-based approach for automatic suicide risk assessment.…

The increasing use of Large Language Models (LLMs) in a large variety of domains has sparked worries about how easily they can perpetuate stereotypes and contribute to the generation of biased content. With a focus on gender and…

Language model prompt optimization research has shown that semantically and grammatically well-formed manually crafted prompts are routinely outperformed by automatically generated token sequences with no apparent meaning or syntactic…

Numerous models have shown great success in the fields of speech recognition as well as speech synthesis, but models for speech to speech processing have not been heavily explored. We propose Speech to Speech Synthesis Network (STSSN), a…

Text-to-image (T2I) generative models are largely used in AI-powered real-world applications and value creation. However, their strategic deployment raises critical concerns for responsible AI management, particularly regarding the…

The gender of any voice user interface is a key element of its perceived identity. Recently, there has been increasing interest in interfaces where the gender is ambiguous rather than clearly identifying as female or male. This work…

Research on bias in Text-to-Image (T2I) models has primarily focused on demographic representation and stereotypical attributes, overlooking a fundamental question: how does grammatical gender influence visual representation across…

Abusive language detection models tend to have a problem of being biased toward identity words of a certain group of people because of imbalanced training datasets. For example, "You are a good woman" was considered "sexist" when trained on…

Self-supervised models for speech processing emerged recently as popular foundation blocks in speech processing pipelines. These models are pre-trained on unlabeled audio data and then used in speech processing downstream tasks such as…

As recent text-to-speech (TTS) systems have been rapidly improved in speech quality and generation speed, many researchers now focus on a more challenging issue: expressive TTS. To control speaking styles, existing expressive TTS models use…

System prompts in Large Language Models (LLMs) are predefined directives that guide model behaviour, taking precedence over user inputs in text processing and generation. LLM deployers increasingly use them to ensure consistent responses…

Recently, and under the umbrella of Responsible AI, efforts have been made to develop gender-ambiguous synthetic speech to represent with a single voice all individuals in the gender spectrum. However, research efforts have completely…

Gender-neutral pronouns have recently been introduced in many languages to a) include non-binary people and b) as a generic singular. Recent results from psycholinguistics suggest that gender-neutral pronouns (in Swedish) are not associated…