Related papers: Progressive Voice Trigger Detection: Accuracy vs L…

The prosody of a spoken word is determined by its surrounding context. In incremental text-to-speech synthesis, where the synthesizer produces an output before it has access to the complete input, the full context is often unknown which can…

To understand how well a large language model captures certain semantic or syntactic features, researchers typically apply probing classifiers. However, the accuracy of these classifiers is critical for the correct interpretation of the…

Target speech extraction (TSE) extracts the speech of a target speaker in a mixture given auxiliary clues characterizing the speaker, such as an enrollment utterance. TSE addresses thus the challenging problem of simultaneously performing…

The mechanism proposed here is for real-time speaker change detection in conversations, which firstly trains a neural network text-independent speaker classifier using in-domain speaker data. Through the network, features of conversational…

The audio segmentation mismatch between training data and those seen at run-time is a major problem in direct speech translation. Indeed, while systems are usually trained on manually segmented corpora, in real use cases they are often…

Latent Action Models (LAMs) have rapidly gained traction as an important component in the pre-training pipelines of leading Vision-Language-Action models. However, they fail when observations contain action-correlated distractors, often…

With the wide adoption of automated speech recognition (ASR) systems, it is increasingly important to test and improve ASR systems. However, collecting and executing speech test cases is usually expensive and time-consuming, motivating us…

Recent studies have proposed the use of Text-To-Speech (TTS) systems to automatically synthesise speech test cases on a scale and uncover a large number of failures in ASR systems. However, the failures uncovered by synthetic test cases may…

Speech enhancement (SE) systems are typically evaluated using a variety of instrumental metrics. The use of automatic speech recognition (ASR) systems to evaluate SE performance is common in literature, usually in terms of word error rate…

This paper integrates a voice activity detection (VAD) function with end-to-end automatic speech recognition toward an online speech interface and transcribing very long audio recordings. We focus on connectionist temporal classification…

Audio DeepFakes are utterances generated with the use of deep neural networks. They are highly misleading and pose a threat due to use in fake news, impersonation, or extortion. In this work, we focus on increasing accessibility to the…

Speaker verification systems are vulnerable to spoofing attacks which presents a major problem in their real-life deployment. To date, most of the proposed synthetic speech detectors (SSDs) have weighted the importance of different segments…

With the growing requirement for natural human-computer interaction, speech-based systems receive increasing attention as speech is one of the most common forms of daily communication. However, the existing speech models still experience…

Human talkers often address listeners with language-comprehension challenges, such as hard-of-hearing or non-native adults, by globally slowing down their speech. However, it remains unclear whether this strategy actually makes speech more…

Modern toxic speech detectors are incompetent in recognizing disguised offensive language, such as adversarial attacks that deliberately avoid known toxic lexicons, or manifestations of implicit bias. Building a large annotated dataset for…

A principal decides whether to approve an agent based on a noisy signal (e.g., test scores) generated by the agent. High-quality agents can produce high signals on average at lower cost, but the realizations are subject to noise that…

Large language models (LLMs) are proven to benefit a lot from retrieval-augmented generation (RAG) in alleviating hallucinations confronted with knowledge-intensive questions. RAG adopts information retrieval techniques to inject external…

Backdoor attacks pose a critical threat by embedding hidden triggers into inputs, causing models to misclassify them into target labels. While extensive research has focused on mitigating these attacks in object recognition models through…

Contextual automatic speech recognition (ASR) with Speech-LLMs is typically trained with oracle conversation history, but relies on error-prone history at inference, causing a train-test mismatch in the context channel that we term…

Thanks to recent advances in deep learning, sophisticated generation tools exist, nowadays, that produce extremely realistic synthetic speech. However, malicious uses of such tools are possible and likely, posing a serious threat to our…