相关论文: Voice, Bias, and Coreference: An Interpretability …

This study addresses the issue of speaker gender bias in Speech Translation (ST) systems, which can lead to offensive and inaccurate translations. The masculine bias often found in large-scale ST systems is typically perpetuated through…

When translating from notional gender languages (e.g., English) into grammatical gender languages (e.g., Italian), the generated translation requires explicit gender assignments for various words, including those referring to the speaker.…

Recent studies on interpreting the hidden states of speech models have shown their ability to capture speaker-specific features, including gender. Does this finding also hold for speech translation (ST) models? If so, what are the…

When translating words referring to the speaker, speech translation (ST) systems should not resort to default masculine generics nor rely on potentially misleading vocal traits. Rather, they should assign gender according to the speakers'…

Translating from languages without productive grammatical gender like English into gender-marked languages is a well-known difficulty for machines. This difficulty is also due to the fact that the training data on which models are built…

In automatic speech translation (ST), traditional cascade approaches involving separate transcription and translation steps are giving ground to increasingly competitive and more robust direct solutions. In particular, by translating speech…

Speech Integrated Large Language Models (SILLMs) combine large language models with speech perception to perform diverse tasks, such as emotion recognition to speaker verification, demonstrating universal audio understanding capability.…

Similar to text-based Large Language Models (LLMs), Speech-LLMs exhibit emergent abilities and context awareness. However, whether these similarities extend to gender bias remains an open question. This study proposes a methodology…

Speech Large Language Models (SpeechLLMs) process spoken input directly, retaining cues such as accent and perceived gender that were previously removed in cascaded pipelines. This introduces speaker identity dependent variation in…

The rapid growth of Speech Emotion Recognition (SER) has diverse global applications, from improving human-computer interactions to aiding mental health diagnostics. However, SER models might contain social bias toward gender, leading to…

The widespread of powerful personal devices capable of collecting voice of their users has opened the opportunity to build speaker adapted speech recognition system (ASR) or to participate to collaborative learning of ASR. In both cases,…

Gender bias is largely recognized as a problematic phenomenon affecting language technologies, with recent studies underscoring that it might surface differently across languages. However, most of current evaluation practices adopt a…

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…

Multilingual representations embed words from many languages into a single semantic space such that words with similar meanings are close to each other regardless of the language. These embeddings have been widely used in various settings,…

Speech-aware Language Models (SpeechLMs) have fundamentally transformed human-AI interaction by enabling voice-based communication, yet they may exhibit acoustic-based gender differentiation where identical questions lead to different…

It is widely known that males and females typically possess different sound characteristics when singing, such as timbre and pitch, but it has never been explored whether these gender-based characteristics lead to a performance disparity in…

Gender-inclusive language is often used with the aim of ensuring that all individuals, regardless of gender, can be associated with certain concepts. While psycholinguistic studies have examined its effects in relation to human cognition,…

Multilingual language models were shown to allow for nontrivial transfer across scripts and languages. In this work, we study the structure of the internal representations that enable this transfer. We focus on the representation of gender…

Gender bias in pretrained language models (PLMs) poses significant social and ethical challenges. Despite growing awareness, there is a lack of comprehensive investigation into how different models internally represent and propagate such…

With the growing deployment of large language models (LLMs) across various applications, assessing the influence of gender biases embedded in LLMs becomes crucial. The topic of gender bias within the realm of natural language processing…