Related papers: Dialogue Act Sequence Labeling using Hierarchical …

Sequence labeling architectures use word embeddings for capturing similarity, but suffer when handling previously unseen or rare words. We investigate character-level extensions to such models and propose a novel architecture for combining…

Semantically controlled neural response generation on limited-domain has achieved great performance. However, moving towards multi-domain large-scale scenarios are shown to be difficult because the possible combinations of semantic inputs…

Speech emotion recognition is the task of recognizing the speaker's emotional state given a recording of their utterance. While most of the current approaches focus on inferring emotion from isolated utterances, we argue that this is not…

Semantic role labeling is primarily used to identify predicates, arguments, and their semantic relationships. Due to the limitations of modeling methods and the conditions of pre-identified predicates, previous work has focused on the…

In Automatic Speech Recognition it is still challenging to learn useful intermediate representations when using high-level (or abstract) target units such as words. For that reason, character or phoneme based systems tend to outperform…

Recurrent neural network (RNN) based character-level language models (CLMs) are extremely useful for modeling out-of-vocabulary words by nature. However, their performance is generally much worse than the word-level language models (WLMs),…

Commonly used automatic speech recognition (ASR) systems can be classified into frame-synchronous and label-synchronous categories, based on whether the speech is decoded on a per-frame or per-label basis. Frame-synchronous systems, such as…

Motivated by a project to create a system for people who are deaf or hard-of-hearing that would use automatic speech recognition (ASR) to produce real-time text captions of spoken English during in-person meetings with hearing individuals,…

In this paper, a hierarchical attention network to generate utterance-level embeddings (H-vectors) for speaker identification is proposed. Since different parts of an utterance may have different contributions to speaker identities, the use…

In lexical semantics, full-sentence segmentation and segment labeling of various phenomena are generally treated separately, despite their interdependence. We hypothesize that a unified lexical semantic recognition task is an effective way…

Recent works show that discourse analysis benefits from modeling intra- and inter-sentential levels separately, where proper representations for text units of different granularities are desired to capture both the meaning of text units and…

Neural network based approaches for sentence relation modeling automatically generate hidden matching features from raw sentence pairs. However, the quality of matching feature representation may not be satisfied due to complex semantic…

We apply sequence-to-sequence model to mitigate the impact of speech recognition errors on open domain end-to-end dialog generation. We cast the task as a domain adaptation problem where ASR transcriptions and original text are in two…

Detecting emotion from dialogue is a challenge that has not yet been extensively surveyed. One could consider the emotion of each dialogue turn to be independent, but in this paper, we introduce a hierarchical approach to classify emotion,…

Conversational automatic speech recognition (ASR) is a task to recognize conversational speech including multiple speakers. Unlike sentence-level ASR, conversational ASR can naturally take advantages from specific characteristics of…

We propose an architecture to jointly learn word and label embeddings for slot filling in spoken language understanding. The proposed approach encodes labels using a combination of word embeddings and straightforward word-label association…

We propose Sentence Level Recurrent Topic Model (SLRTM), a new topic model that assumes the generation of each word within a sentence to depend on both the topic of the sentence and the whole history of its preceding words in the sentence.…

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…

Existing approaches to dialogue state tracking rely on pre-defined ontologies consisting of a set of all possible slot types and values. Though such approaches exhibit promising performance on single-domain benchmarks, they suffer from…

Several works in computer vision have demonstrated the effectiveness of active learning for adapting the recognition model when new unlabeled data becomes available. Most of these works consider that labels obtained from the annotator are…