Related papers: E2E Spoken Entity Extraction for Virtual Agents
The goal of spoken language understanding (SLU) systems is to determine the meaning of the input speech signal, unlike speech recognition which aims to produce verbatim transcripts. Advances in end-to-end (E2E) speech modeling have made it…
Successful Machine Learning based Named Entity Recognition models could fail on texts from some special domains, for instance, Chinese addresses and e-commerce titles, where requires adequate background knowledge. Such texts are also…
Process-aware information systems offer extensive advantages to companies, facilitating planning, operations, and optimization of day-to-day business activities. However, the time-consuming but required step of designing formal business…
Speech is the most natural way of expressing ourselves as humans. Identifying emotion from speech is a nontrivial task due to the ambiguous definition of emotion itself. Speaker Emotion Recognition (SER) is essential for understanding human…
Personalized speech enhancement (PSE) models can improve the audio quality of teleconferencing systems by adapting to the characteristics of a speaker's voice. However, most existing methods require a separate speaker embedding model to…
Recently, end-to-end (E2E) automatic speech recognition (ASR) models have made great strides and exhibit excellent performance in general speech recognition. However, there remain several challenging scenarios that E2E models are not…
We introduce a new entity typing task: given a sentence with an entity mention, the goal is to predict a set of free-form phrases (e.g. skyscraper, songwriter, or criminal) that describe appropriate types for the target entity. This…
Recent work has shown that NLP tasks such as Relation Extraction (RE) can be recasted as Textual Entailment tasks using verbalizations, with strong performance in zero-shot and few-shot settings thanks to pre-trained entailment models. The…
Spoken language understanding (SLU) tasks are usually solved by first transcribing an utterance with automatic speech recognition (ASR) and then feeding the output to a text-based model. Recent advances in self-supervised representation…
End-to-end (E2E) spoken language understanding (SLU) systems predict utterance semantics directly from speech using a single model. Previous work in this area has focused on targeted tasks in fixed domains, where the output semantic…
Target speech extraction, which extracts the speech of a target speaker in a mixture given auxiliary speaker clues, has recently received increased interest. Various clues have been investigated such as pre-recorded enrollment utterances,…
Predicting the next utterance in dialogue is contingent on encoding of users' input text to generate appropriate and relevant response in data-driven approaches. Although the semantic and syntactic quality of the language generated is…
Extracting entities and relations is an essential task of information extraction. Triplets extracted from a sentence might overlap with each other. Previous methods either did not address the overlapping issues or solved overlapping issues…
Pre-trained transformer models shine in many natural language processing tasks and therefore are expected to bear the representation of the input sentence or text meaning. These sentence-level embeddings are also important in…
Audio Word2Vec offers vector representations of fixed dimensionality for variable-length audio segments using Sequence-to-sequence Autoencoder (SA). These vector representations are shown to describe the sequential phonetic structures of…
Named entity recognition (NER) is highly sensitive to sentential syntactic and semantic properties where entities may be extracted according to how they are used and placed in the running text. To model such properties, one could rely on…
A number of recent studies have started to investigate how speech systems can be trained on untranscribed speech by leveraging accompanying images at training time. Examples of tasks include keyword prediction and within- and across-mode…
Understanding the meaning of text often involves reasoning about entities and their relationships. This requires identifying textual mentions of entities, linking them to a canonical concept, and discerning their relationships. These tasks…
Named Entity Recognition (NER) from speech is among Spoken Language Understanding (SLU) tasks, aiming to extract semantic information from the speech signal. NER from speech is usually made through a two-step pipeline that consists of (1)…
Recent advancements in Text-to-Speech (TTS) systems have enabled the generation of natural and expressive speech from textual input. Accented TTS aims to enhance user experience by making the synthesized speech more relatable to minority…