Related papers: Lexico-acoustic Neural-based Models for Dialog Act…
We present a model for pragmatically describing scenes, in which contrastive behavior results from a combination of inference-driven pragmatics and learned semantics. Like previous learned approaches to language generation, our model uses a…
Linguistic pragmatics state that a conversation's underlying speech acts can constrain the type of response which is appropriate at each turn in the conversation. When generating dialogue responses, neural dialogue agents struggle to…
Proposal of large-scale datasets has facilitated research on deep neural models for news summarization. Deep learning can also be potentially useful for spoken dialogue summarization, which can benefit a range of real-life scenarios…
We introduce the new task of Acoustic Question Answering (AQA) to promote research in acoustic reasoning. The AQA task consists of analyzing an acoustic scene composed by a combination of elementary sounds and answering questions that…
Speech perception involves storing and integrating sequentially presented items. Recent work in cognitive neuroscience has identified temporal and contextual characteristics in humans' neural encoding of speech that may facilitate this…
Speech is a fundamental means of communication that can be seen to provide two channels for transmitting information: the lexical channel of which words are said, and the non-lexical channel of how they are spoken. Both channels shape…
Humans often employ figurative language use in communication, including during interactions with dialog systems. Thus, it is important for real-world dialog systems to be able to handle popular figurative language constructs like metaphor…
This paper presents a context-aware framework for feature selection and classification procedures to realize a fast and accurate audio event annotation and classification. The context-aware design starts with exploring feature extraction…
Automatic pronunciation evaluation plays an important role in pronunciation training and second language education. This field draws heavily on concepts from automatic speech recognition (ASR) to quantify how close the pronunciation of…
In automatic speech recognition, often little training data is available for specific challenging tasks, but training of state-of-the-art automatic speech recognition systems requires large amounts of annotated speech. To address this…
Achieving pronunciation proficiency in a second language (L2) remains a challenge, despite the development of Computer-Assisted Pronunciation Training (CAPT) systems. Traditional CAPT systems often provide unintuitive feedback that lacks…
There are two paradigms of emotion representation, categorical labeling and dimensional description in continuous space. Therefore, the emotion recognition task can be treated as a classification or regression. The main aim of this study is…
Most human interactions occur in the form of spoken conversations where the semantic meaning of a given utterance depends on the context. Each utterance in spoken conversation can be represented by many semantic and speaker attributes, and…
Speech representation and modelling in high-dimensional spaces of acoustic waveforms, or a linear transformation thereof, is investigated with the aim of improving the robustness of automatic speech recognition to additive noise. The…
In a noisy environment, a lossy speech signal can be automatically restored by a listener if he/she knows the language well. That is, with the built-in knowledge of a "language model", a listener may effectively suppress noise interference…
This paper analyses language modeling in spoken dialogue systems for accessing a database. The use of several language models obtained by exploiting dialogue predictions gives better results than the use of a single model for the whole…
It has been argued that humans rapidly adapt their lexical and syntactic expectations to match the statistics of the current linguistic context. We provide further support to this claim by showing that the addition of a simple adaptation…
Most prior work in dialogue modeling has been on written conversations mostly because of existing data sets. However, written dialogues are not sufficient to fully capture the nature of spoken conversations as well as the potential speech…
Current dialogue summarization systems usually encode the text with a number of general semantic features (e.g., keywords and topics) to gain more powerful dialogue modeling capabilities. However, these features are obtained via open-domain…
An open challenge in constructing dialogue systems is developing methods for automatically learning dialogue strategies from large amounts of unlabelled data. Recent work has proposed Next-Utterance-Classification (NUC) as a surrogate task…