相关论文: Jointly Encoding Word Confusion Network and Dialog…

Conversational speech, while being unstructured at an utterance level, typically has a macro topic which provides larger context spanning multiple utterances. The current language models in speech recognition systems using recurrent neural…

The effective exploitation of richer contextual information in language models (LMs) is a long-standing research problem for automatic speech recognition (ASR). A cross-utterance LM (CULM) is proposed in this paper, which augments the input…

Domain adaptation or transfer learning using pre-trained language models such as BERT has proven to be an effective approach for many natural language processing tasks. In this work, we propose to formulate word sense disambiguation as a…

In this work, we propose a new automatic speech recognition (ASR) system based on feature learning and an end-to-end training procedure for air traffic control (ATC) systems. The proposed model integrates the feature learning block,…

Current researches on spoken language understanding (SLU) heavily are limited to a simple setting: the plain text-based SLU that takes the user utterance as input and generates its corresponding semantic frames (e.g., intent and slots).…

Spoken language understanding (SLU) requires a model to analyze input acoustic signal to understand its linguistic content and make predictions. To boost the models' performance, various pre-training methods have been proposed to learn rich…

The University of Sheffield (USFD) participated in the International Workshop for Spoken Language Translation (IWSLT) in 2014. In this paper, we will introduce the USFD SLT system for IWSLT. Automatic speech recognition (ASR) is achieved by…

Language models (LMs) pre-trained on massive amounts of text, in particular bidirectional encoder representations from Transformers (BERT), generative pre-training (GPT), and GPT-2, have become a key technology for many natural language…

Significant performance degradation of automatic speech recognition (ASR) systems is observed when the audio signal contains cross-talk. One of the recently proposed approaches to solve the problem of multi-speaker ASR is the deep…

The pre-trained speech encoder wav2vec 2.0 performs very well on various spoken language understanding (SLU) tasks. However, on many tasks, it trails behind text encoders with textual input. To improve the understanding capability of SLU…

Spoken language understanding, which extracts intents and/or semantic concepts in utterances, is conventionally formulated as a post-processing of automatic speech recognition. It is usually trained with oracle transcripts, but needs to…

Modeling the errors of a speech recognizer can help simulate errorful recognized speech data from plain text, which has proven useful for tasks like discriminative language modeling, improving robustness of NLP systems, where limited or…

This paper presents the use of non-autoregressive (NAR) approaches for joint automatic speech recognition (ASR) and spoken language understanding (SLU) tasks. The proposed NAR systems employ a Conformer encoder that applies connectionist…

Attention-based encoder-decoder architectures such as Listen, Attend, and Spell (LAS), subsume the acoustic, pronunciation and language model components of a traditional automatic speech recognition (ASR) system into a single neural…

Spoken Language Understanding (SLU) mainly involves two tasks, intent detection and slot filling, which are generally modeled jointly in existing works. However, most existing models fail to fully utilize co-occurrence relations between…

Self-supervised automatic speech recognition (SSL-ASR) is an ASR approach that uses speech encoders pretrained on large amounts of unlabeled audio (e.g., wav2vec2.0 or HuBERT) and then fine-tunes them with limited labeled data to perform…

Word vector representations are a crucial part of Natural Language Processing (NLP) and Human Computer Interaction. In this paper, we propose a novel word vector representation, Confusion2Vec, motivated from the human speech production and…

The Recurrent Neural Network-Transducer (RNN-T) is widely adopted in end-to-end (E2E) automatic speech recognition (ASR) tasks but depends heavily on large-scale, high-quality annotated data, which are often costly and difficult to obtain.…

Due to recent technical and scientific advances, we have a wealth of information hidden in unstructured text data such as offline/online narratives, research articles, and clinical reports. To mine these data properly, attributable to their…

End-to-end Spoken Language Understanding (E2E SLU) has attracted increasing interest due to its advantages of joint optimization and low latency when compared to traditionally cascaded pipelines. Existing E2E SLU models usually follow a…