Related papers: Back Transcription as a Method for Evaluating Robu…

Recently, language models have demonstrated strong performance on various natural language understanding tasks. Language models trained on large human-generated corpus encode not only a significant amount of human knowledge, but also the…

Generative spoken language models pretrained on large-scale raw audio can continue a speech prompt with appropriate content while preserving attributes like speaker and emotion, serving as foundation models for spoken dialogue. In prior…

State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. They are prone to overfitting and poor generalization when…

Neural Machine Translation (NMT) models have been proved strong when translating clean texts, but they are very sensitive to noise in the input. Improving NMT models robustness can be seen as a form of "domain" adaption to noise. The…

Lexically constrained decoding for machine translation has shown to be beneficial in previous studies. Unfortunately, constraints provided by users may contain mistakes in real-world situations. It is still an open question that how to…

Neural Machine Translation (MT) has radically changed the way systems are developed. A major difference with the previous generation (Phrase-Based MT) is the way monolingual target data, which often abounds, is used in these two paradigms.…

Natural language understanding (NLU) and natural language generation (NLG) are two fundamental and related tasks in building task-oriented dialogue systems with opposite objectives: NLU tackles the transformation from natural language to…

When evaluating the performance of automatic speech recognition models, usually word error rate within a certain dataset is used. Special care must be taken in understanding the dataset in order to report realistic performance numbers. We…

Text-to-Speech synthesis systems are generally evaluated using Mean Opinion Score (MOS) tests, where listeners score samples of synthetic speech on a Likert scale. A major drawback of MOS tests is that they only offer a general measure of…

Embedding paralinguistic properties is a challenging task as there are only a few hours of training data available for domains such as emotional speech. One solution to this problem is to pretrain a general self-supervised speech…

We consider the problem of making machine translation more robust to character-level variation at the source side, such as typos. Existing methods achieve greater coverage by applying subword models such as byte-pair encoding (BPE) and…

Spoken language understanding (SLU) systems in conversational AI agents often experience errors in the form of misrecognitions by automatic speech recognition (ASR) or semantic gaps in natural language understanding (NLU). These errors…

Translate-test is a popular technique to improve the performance of multilingual language models. This approach works by translating the input into English using an external machine translation system, and running inference over the…

We investigate the efficiency of two very different spoken term detection approaches for transcription when the available data is insufficient to train a robust ASR system. This work is grounded in very low-resource language documentation…

A lot of work has been done to build text-based language models for performing different NLP tasks, but not much research has been done in the case of audio-based language models. This paper proposes a Convolutional Autoencoder based neural…

We propose transfer learning as a method for analyzing the encoding of grammatical structure in neural language models. We train LSTMs on non-linguistic data and evaluate their performance on natural language to assess which kinds of data…

In modular dialogue systems, natural language understanding (NLU) and natural language generation (NLG) are two critical components, where NLU extracts the semantics from the given texts and NLG is to construct corresponding natural…

Given the fast development of analysis techniques for NLP and speech processing systems, few systematic studies have been conducted to compare the strengths and weaknesses of each method. As a step in this direction we study the case of…

As neural language models achieve human-comparable performance on Machine Reading Comprehension (MRC) and see widespread adoption, ensuring their robustness in real-world scenarios has become increasingly important. Current robustness…

The emergence of pre-trained models has significantly impacted Natural Language Processing (NLP) and Computer Vision to relational datasets. Traditionally, these models are assessed through fine-tuned downstream tasks. However, this raises…