Related papers: Speaker Identification Experiments Under Gender De…

Speaker change detection is an important task in multi-party interactions such as meetings and conversations. In this paper, we address the speaker change detection task from the perspective of sequence transduction. Specifically, we…

Self-supervised speech models learn representations that capture both content and speaker information. Yet this entanglement creates problems: content tasks suffer from speaker bias, and privacy concerns arise when speaker identity leaks…

While instruction-tuned language models have demonstrated impressive zero-shot generalization, these models often struggle to generate accurate responses when faced with instructions that fall outside their training set. This paper presents…

In this work, we propose a multi-target backdoor attack against speaker identification using position-independent clicking sounds as triggers. Unlike previous single-target approaches, our method targets up to 50 speakers simultaneously,…

This paper addresses spoken language identification (SLI) and speech recognition of multilingual broadcast and institutional speech, real application scenarios that have been rarely addressed in the SLI literature. Observing that in these…

Speech 'in-the-wild' is a handicap for speaker recognition systems due to the variability induced by real-life conditions, such as environmental noise and the emotional state of the speaker. Taking advantage of the principles of…

Voice conversion (VC) consists of digitally altering the voice of an individual to manipulate part of its content, primarily its identity, while maintaining the rest unchanged. Research in neural VC has accomplished considerable…

Changing speaker names consistently throughout a dialogue should not affect its meaning and corresponding outputs for text generation from dialogues. However, pre-trained language models, serving as the backbone for dialogue-processing…

Speaker recognition is a well known and studied task in the speech processing domain. It has many applications, either for security or speaker adaptation of personal devices. In this paper, we present a new paradigm for automatic speaker…

Current language models decode text token by token according to probabilistic distribution, and determining the appropriate candidates for the next token is crucial to ensure generation quality. This study introduces adaptive decoding, a…

With the increase in the availability of speech from varied domains, it is imperative to use such out-of-domain data to improve existing speech systems. Domain adaptation is a prominent pre-processing approach for this. We investigate it…

Word embedding, which converts words into numerical values, is an important natural language processing technique and widely used. One of the serious problems of word embedding is that the bias will be learned and affect the model if the…

In the fields of security systems, forensic investigations, and personalized services, the importance of speech as a fundamental human input outweighs text-based interactions. This research delves deeply into the complex field of Speaker…

End-to-end Automatic Speech Recognition (ASR) models are commonly trained over spoken utterances using optimization methods like Stochastic Gradient Descent (SGD). In distributed settings like Federated Learning, model training requires…

In recent years, end-to-end speech recognition has emerged as a technology that integrates the acoustic, pronunciation dictionary, and language model components of the traditional Automatic Speech Recognition model. It is possible to…

The objective of this work is to train noise-robust speaker embeddings adapted for speaker diarisation. Speaker embeddings play a crucial role in the performance of diarisation systems, but they often capture spurious information such as…

Speech recognition is very challenging in student learning environments that are characterized by significant cross-talk and background noise. To address this problem, we present a bilingual speech recognition system that uses an…

Speech signals encompass various information across multiple levels including content, speaker, and style. Disentanglement of these information, although challenging, is important for applications such as voice conversion. The contrastive…

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…

As for other forms of AI, speech recognition has recently been examined with respect to performance disparities across different user cohorts. One approach to achieve fairness in speech recognition is to (1) identify speaker cohorts that…