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

Spoken language understanding (SLU) tasks involve mapping from speech audio signals to semantic labels. Given the complexity of such tasks, good performance might be expected to require large labeled datasets, which are difficult to collect…

In spite of great advancements of machine reading comprehension (RC), existing RC models are still vulnerable and not robust to different types of adversarial examples. Neural models over-confidently predict wrong answers to semantic…

Automatic speech recognition (ASR) systems, increasingly prevalent in education, healthcare, employment, and mobile technology, face significant challenges in inclusivity, particularly for the 80 million-strong global community of people…

The subtleties of human perception, as measured by vision scientists through the use of psychophysics, are important clues to the internal workings of visual recognition. For instance, measured reaction time can indicate whether a visual…

Without real bilingual corpus available, unsupervised Neural Machine Translation (NMT) typically requires pseudo parallel data generated with the back-translation method for the model training. However, due to weak supervision, the pseudo…

Human intelligence exhibits compositional generalization (i.e., the capacity to understand and produce unseen combinations of seen components), but current neural seq2seq models lack such ability. In this paper, we revisit iterative…

While achieving state-of-the-art results in multiple tasks and languages, translation-based cross-lingual transfer is often overlooked in favour of massively multilingual pre-trained encoders. Arguably, this is due to its main limitations:…

Speech tokenization serves as the foundation of speech language model (LM), enabling them to perform various tasks such as spoken language modeling, text-to-speech, speech-to-text, etc. Most speech tokenizers are trained independently of…

Consistency is a long standing issue faced by dialogue models. In this paper, we frame the consistency of dialogue agents as natural language inference (NLI) and create a new natural language inference dataset called Dialogue NLI. We…

Large, pre-trained representation models trained using self-supervised learning have gained popularity in various fields of machine learning because they are able to extract high-quality salient features from input data. As such, they have…

Code understanding is a foundational capability in software engineering tools and developer workflows. However, most existing systems are designed for English-speaking users interacting via keyboards, which limits accessibility in…

Negative transfer in training of acoustic models for automatic speech recognition has been reported in several contexts such as domain change or speaker characteristics. This paper proposes a novel technique to overcome negative transfer by…

End-to-end spoken language understanding (SLU) systems that process human-human or human-computer interactions are often context independent and process each turn of a conversation independently. Spoken conversations on the other hand, are…

Text-to-speech models trained on large-scale datasets have demonstrated impressive in-context learning capabilities and naturalness. However, control of speaker identity and style in these models typically requires conditioning on reference…

Natural Language Processing (NLP) has transformed various fields beyond linguistics by applying techniques originally developed for human language to the analysis of biological sequences. This review explores the application of NLP methods…

We present a training method with linguistic speech regularization that improves the robustness of spontaneous speech synthesis methods with filled pause (FP) insertion. Spontaneous speech synthesis is aimed at producing speech with…

In this paper, we investigate the use of linguistically motivated and computationally efficient structured language models for reranking N-best hypotheses in a statistical machine translation system. These language models, developed from…

Modern speech synthesis systems have improved significantly, with synthetic speech being indistinguishable from real speech. However, efficient and holistic evaluation of synthetic speech still remains a significant challenge. Human…

Diffusion models have shown exceptional scaling properties in the image synthesis domain, and initial attempts have shown similar benefits for applying diffusion to unconditional text synthesis. Denoising diffusion models attempt to…

Single-channel speech enhancement approaches do not always improve automatic recognition rates in the presence of noise, because they can introduce distortions unhelpful for recognition. Following a trend towards end-to-end training of…