25 accepted papers
Since Text-to-Speech systems typically don't produce waveforms directly, recent spoof detection studies use resynthesized waveforms from vocoders and neural audio codecs to simulate an attacker. Unlike vocoders, which are specifically designed for speech synthesis, neural audio codecs were originall…
Language in the Arab world presents a complex diglossic and multilingual setting, involving the use of Modern Standard Arabic, various dialects and sub-dialects, as well as multiple European languages. This diverse linguistic landscape has given rise to code-switching, both within Arabic varieties a…
Explainable artificial intelligence (XAI) aims to make machine learning models more transparent. While many approaches focus on generating explanations post-hoc, interpretable approaches, which generate the explanations intrinsically alongside the predictions, are relatively rare. In this work, we i…
Traditional speech enhancement methods often oversimplify the task of restoration by focusing on a single type of distortion. Generative models that handle multiple distortions frequently struggle with phone reconstruction and high-frequency harmonics, leading to breathing and gasping artifacts that…
Given the conflicting expectations users have for how a dialog agent should sound and behave, there is no one-size-fits-all option for dialog system design. Therefore, adaptation is critical to ensure successful and enjoyable interactions. However, it is not yet clear what the effects of behavioral…
The increasing sophistication of deepfake audio generation technologies makes it important to develop robust fake audio detection systems that can adapt over time. This study examines how various factors impact the performance of detection systems in a continual learning setting. We focus on factors…
Attribution scores indicate the importance of different input parts and can, thus, explain model behaviour. Currently, prompt-based models are gaining popularity, i.a., due to their easier adaptability in low-resource settings. However, the quality of attribution scores extracted from prompt-based m…
The large success of deep learning based methods in Visual Question Answering (VQA) has concurrently increased the demand for explainable methods. Most methods in Explainable Artificial Intelligence (XAI) focus on generating post-hoc explanations rather than taking an intrinsic approach, the latter…
Although language models (LMs) have boosted the performance of Question Answering, they still need plenty of data. Data annotation, in contrast, is a time-consuming process. This especially applies to Question Answering, where possibly large documents have to be parsed and annotated with questions a…
Conversational Tree Search (Väth et al., 2023) is a recent approach to controllable dialog systems, where domain experts shape the behavior of a Reinforcement Learning agent through a dialog tree. The agent learns to efficiently navigate this tree, while adapting to information needs, e.g., domain f…
In recent years machine translation has become very successful for high-resource language pairs. This has also sparked new interest in research on the automatic translation of low-resource languages, including Indigenous languages. However, the latter are deeply related to the ethnic and cultural gr…
Word-level saliency explanations (“heat maps over words”) are often used to communicate feature-attribution in text-based models. Recent studies found that superficial factors such as word length can distort human interpretation of the communicated saliency scores. We conduct a user study to investi…
Prosody is closely linked to the identity of a speaker, leading to individual pitch and intonation patterns. Therefore, it is challenging in speaker anonymization to generate speech utterances that both keep the original audio’s main prosodic structure and preserve the speaker’s privacy. In this pap…
Meta-learning has made tremendous progress in recent years and was demonstrated to be particularly suitable in low-resource settings where training data is very limited. However, meta-learning models still require large amounts of training tasks to achieve good generalisation. Since labelled trainin…
As Automatic Speech Processing (ASR) systems are getting better, there is an increasing interest of using the ASR output to do downstream Natural Language Processing (NLP) tasks. However, there are few open source toolkits that can be used to generate reproducible results on different Spoken Languag…
On the way towards general Visual Question Answering (VQA) systems that are able to answer arbitrary questions, the need arises for evaluation beyond single-metric leaderboards for specific datasets. To this end, we propose a browser-based benchmarking tool for researchers and challenge organizers,…
In this work we take on the challenge of rare word recognition in end-to-end (E2E) automatic speech recognition (ASR) by integrating a meta learning mechanism into an E2E ASR system, enabling few-shot adaptation. We propose a novel method of generating embeddings for speech, changes to four meta lea…
Recently, leveraging pre-trained Transformer based language models in down stream, task specific models has advanced state of the art results in natural language understanding tasks. However, only a little research has explored the suitability of this approach in low resource settings with less than…
This paper presents our latest investigation on modeling backchannel in conversations. Motivated by a proactive backchanneling theory, we aim at developing a system which acts as a proactive listener by inserting backchannels, such as continuers and assessment, to influence speakers. Our model takes…
This paper presents our latest investigations on dialog act (DA) classification on automatically generated transcriptions. We propose a novel approach that combines convolutional neural networks (CNNs) and conditional random fields (CRFs) for context modeling in DA classification. We explore the imp…
In this paper we present our findings on how representation learning on large unlabeled speech corpora can be beneficially utilized for speech emotion recognition (SER). Prior work on representation learning for SER mostly focused on the relatively small emotional speech datasets without making use…
Research on multilingual speech emotion recognition faces the problem that most available speech corpora differ from each other in important ways, such as annotation methods or interaction scenarios. These inconsistencies complicate building a multilingual system. We present results for cross-lingua…
Audiovisual speech recognition (AVSR) is a method to alleviate the adverse effect of noise in the acoustic signal. Leveraging recent developments in deep neural network-based speech recognition, we present an AVSR neural network architecture which is trained end-to-end, without the need to separatel…
Recent works have proposed neural models for dialog act classification in spoken dialogs. However, they have not explored the role and the usefulness of acoustic information. We propose a neural model that processes both lexical and acoustic features for classification. Our results on two benchmark…
This paper presents our latest investigation of recurrent neural networks for the slot filling task of spoken language understanding. We implement a bi-directional Elman-type recurrent neural network which takes the information not only from the past but also from the future context to predict the s…