Related papers: Trainable Adaptive Score Normalization for Automat…

Modeling voice identity is challenging due to its multifaceted nature. In generative speech systems, identity is often assessed using automatic speaker verification (ASV) embeddings, designed for discrimination rather than characterizing…

Scores from traditional confidence classifiers (CCs) in automatic speech recognition (ASR) systems lack universal interpretation and vary with updates to the underlying confidence or acoustic models (AMs). In this work, we build…

Automatic speaker verification (ASV), one of the most important technology for biometric identification, has been widely adopted in security-critical applications. However, ASV is seriously vulnerable to recently emerged adversarial…

Audiovisual active speaker detection (ASD) addresses the task of determining the speech activity of a candidate speaker given acoustic and visual data. Typically, systems model the temporal correspondence of audiovisual cues, such as the…

Automatic Speaker Verification (ASV) suffers from performance degradation in noisy conditions. To address this issue, we propose a novel adversarial learning framework that incorporates noise-disentanglement to establish a noise-independent…

Recent efforts target spoken language models (SLMs) that not only listen but also speak for more natural human-LLM interaction. Joint speech-text modeling is a promising direction to achieve this. However, the effectiveness of recent speech…

Speaker verification, as a biometric authentication mechanism, has been widely used due to the pervasiveness of voice control on smart devices. However, the task of "in-the-wild" speaker verification is still challenging, considering the…

We propose an unsupervised adaptation framework, Self-TAught Recognizer (STAR), which leverages unlabeled data to enhance the robustness of automatic speech recognition (ASR) systems in diverse target domains, such as noise and accents.…

Recent advances in speech foundation models are largely driven by scaling both model size and data, enabling them to perform a wide range of tasks, including speech recognition. Traditionally, ASR models are evaluated using metrics like…

Recent speech enhancement (SE) models increasingly leverage self-supervised learning (SSL) representations for their rich semantic information. Typically, intermediate features are aggregated into a single representation via a lightweight…

In this paper, we propose a novel auxiliary loss function for target-speaker automatic speech recognition (ASR). Our method automatically extracts and transcribes target speaker's utterances from a monaural mixture of multiple speakers…

This paper introduces an active learning (AL) framework for anomalous sound detection (ASD) in machine condition monitoring system. Typically, ASD models are trained solely on normal samples due to the scarcity of anomalous data, leading to…

Speech-enabled systems typically first convert audio to text through an automatic speech recognition (ASR) model and then feed the text to downstream natural language processing (NLP) modules. The errors of the ASR system can seriously…

Logical Access (LA) attacks, also known as audio deepfake attacks, use Text-to-Speech (TTS) or Voice Conversion (VC) methods to generate spoofed speech data. This can represent a serious threat to Automatic Speaker Verification (ASV)…

Word error rate (WER) is a standard metric for the evaluation of Automated Speech Recognition (ASR) systems. However, WER fails to provide a fair evaluation of human perceived quality in presence of spelling variations, abbreviations, or…

Self-supervised pretraining for Automated Speech Recognition (ASR) has shown varied degrees of success. In this paper, we propose to jointly learn representations during pretraining from two different modalities: speech and text. The…

Audio-language models (ALMs) excel in zero-shot audio classification, a task where models classify previously unseen audio clips at test time by leveraging descriptive natural language prompts. We introduce TSPE (Task-Specific Prompt…

Self-supervised learning (SSL)-based speech models are extensively used for full-stack speech processing. However, it has been observed that improving SSL-based speech representations using unlabeled speech for content-related tasks is…

With excellent generalization ability, self-supervised speech models have shown impressive performance on various downstream speech tasks in the pre-training and fine-tuning paradigm. However, as the growing size of pre-trained models,…

Machine anomalous sound detection (ASD) is a valuable technique across various applications. However, its generalization performance is often limited due to challenges in data collection and the complexity of acoustic environments. Inspired…