Related papers: A Two-Step Approach for Data-Efficient French Pron…

The spontaneous behavior that often occurs in conversations makes speech more human-like compared to reading-style. However, synthesizing spontaneous-style speech is challenging due to the lack of high-quality spontaneous datasets and the…

Automatically detecting discourse segments is an important preliminary step towards full discourse parsing. Previous research on discourse segmentation have relied on the assumption that elementary discourse units (EDUs) in a document…

While neural machine translation (NMT) is making good progress in the past two years, tens of millions of bilingual sentence pairs are needed for its training. However, human labeling is very costly. To tackle this training data bottleneck,…

Transformer-based models have recently become very popular for sequence-to-sequence applications such as machine translation and speech recognition. This work proposes a dual-decoder transformer model for low-resource multilingual speech…

The amount of labeled data to train models for speech tasks is limited for most languages, however, the data scarcity is exacerbated for speech translation which requires labeled data covering two different languages. To address this issue,…

We present a cost-effective two-step authentication system that integrates face identification and speaker verification using only a camera and microphone available on common devices. The pipeline first performs face recognition to identify…

End-to-end (E2E) models are becoming increasingly popular for spoken language understanding (SLU) systems and are beginning to achieve competitive performance to pipeline-based approaches. However, recent work has shown that these models…

Recent years have seen exceptional strides in the task of automatic morphological inflection generation. However, for a long tail of languages the necessary resources are hard to come by, and state-of-the-art neural methods that work well…

A common and effective means for improving language model capabilities involves finetuning a ``student'' language model's parameters on generations from a more proficient ``teacher'' model. Termed ``synthetic data'', these generations are…

Research on multilingual speech emotion recognition faces the problem that most available speech corpora differ from each other in important ways, such as annotation methods or interaction scenarios. These inconsistencies complicate…

End-to-end TTS requires a large amount of speech/text paired data to cover all necessary knowledge, particularly how to pronounce different words in diverse contexts, so that a neural model may learn such knowledge accordingly. But in real…

Recent work in incremental learning has introduced diverse approaches to tackle catastrophic forgetting from data augmentation to optimized training regimes. However, most of them focus on very few training steps. We propose a method for…

Prompt-based methods have achieved promising results in most few-shot text classification tasks. However, for readability assessment tasks, traditional prompt methods lackcrucial linguistic knowledge, which has already been proven to be…

Supervised training of speech recognition models requires access to transcribed audio data, which often is not possible due to confidentiality issues. Our approach to this problem is to generate synthetic audio from a text-only corpus using…

Attention-based sequence-to-sequence modeling provides a powerful and elegant solution for applications that need to map one sequence to a different sequence. Its success heavily relies on the availability of large amounts of training data.…

Language models have become a key step to achieve state-of-the art results in many different Natural Language Processing (NLP) tasks. Leveraging the huge amount of unlabeled texts nowadays available, they provide an efficient way to…

Current leading mispronunciation detection and diagnosis (MDD) systems achieve promising performance via end-to-end phoneme recognition. One challenge of such end-to-end solutions is the scarcity of human-annotated phonemes on natural L2…

This study presents a novel zero-shot user-defined keyword spotting model that utilizes the audio-phoneme relationship of the keyword to improve performance. Unlike the previous approach that estimates at utterance level, we use both…

Sentence embedding models play a key role in various Natural Language Processing tasks, such as in Topic Modeling, Document Clustering and Recommendation Systems. However, these models rely heavily on parallel data, which can be scarce for…

This paper presents a novel approach for multi-lingual sentiment classification in short texts. This is a challenging task as the amount of training data in languages other than English is very limited. Previously proposed multi-lingual…