Related papers: A Novel Task-Oriented Text Corpus in Silent Speech…
Speech emotion recognition (SER) has been a popular research topic in human-computer interaction (HCI). As edge devices are rapidly springing up, applying SER to edge devices is promising for a huge number of HCI applications. Although deep…
Recently, retrieval-augmented text generation attracted increasing attention of the computational linguistics community. Compared with conventional generation models, retrieval-augmented text generation has remarkable advantages and…
In the last two decades, the landscape of text generation has undergone tremendous changes and is being reshaped by the success of deep learning. New technologies for text generation ranging from template-based methods to neural…
Dysarthric speech recognition (DSR) enhances the accessibility of smart devices for dysarthric speakers with limited mobility. Previously, DSR research was constrained by the fact that existing datasets typically consisted of isolated…
In speech-applications such as text-to-speech (TTS) or automatic speech recognition (ASR), \emph{text normalization} refers to the task of converting from a \emph{written} representation into a representation of how the text is to be…
Recent publications on automatic-speech-recognition (ASR) have a strong focus on attention encoder-decoder (AED) architectures which tend to suffer from over-fitting in low resource scenarios. One solution to tackle this issue is to…
Spoken language understanding (SLU) treats automatic speech recognition (ASR) and natural language understanding (NLU) as a unified task and usually suffers from data scarcity. We exploit an ASR and NLU joint training method based on meta…
Neural network language model (NNLM) plays an essential role in automatic speech recognition (ASR) systems, especially in adaptation tasks when text-only data is available. In practice, an NNLM is typically trained on a combination of data…
Beyond generating long and topic-coherent paragraphs in traditional captioning tasks, the medical image report composition task poses more task-oriented challenges by requiring both the highly-accurate medical term diagnosis and multiple…
In task-oriented dialogs (TOD), reinforcement learning (RL) algorithms train a model to directly optimize response for task-related metrics. However, RL needs to perform exploration, which can be time-consuming due to the slow…
When a natural language generation (NLG) component is implemented in a real-world task-oriented dialogue system, it is necessary to generate not only natural utterances as learned on training data but also utterances adapted to the dialogue…
Most existing neural network based task-oriented dialogue systems follow encoder-decoder paradigm, where the decoder purely depends on the source texts to generate a sequence of words, usually suffering from instability and poor…
The pervasiveness of intra-utterance code-switching (CS) in spoken content requires that speech recognition (ASR) systems handle mixed language. Designing a CS-ASR system has many challenges, mainly due to data scarcity, grammatical…
Natural language generation (NLG) is a critical component of spoken dialogue and it has a significant impact both on usability and perceived quality. Most NLG systems in common use employ rules and heuristics and tend to generate rigid and…
A major obstacle to the wide-spread adoption of neural retrieval models is that they require large supervised training sets to surpass traditional term-based techniques, which are constructed from raw corpora. In this paper, we propose an…
Speech emotion recognition (SER) systems find applications in various fields such as healthcare, education, and security and defense. A major drawback of these systems is their lack of generalization across different conditions. This…
Lexically constrained text generation is one of the constrained text generation tasks, which aims to generate text that covers all the given constraint lexicons. While the existing approaches tackle this problem using a lexically…
In text-to-speech synthesis, the ability to control voice characteristics is vital for various applications. By leveraging thriving text prompt-based generation techniques, it should be possible to enhance the nuanced control of voice…
End-to-end automatic speech recognition (ASR) systems are increasingly popular due to their relative architectural simplicity and competitive performance. However, even though the average accuracy of these systems may be high, the…
This paper summarizes our work on the first track of the ninth Dialog System Technology Challenge (DSTC 9), "Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access". The goal of the task is to generate…