Related papers: SegAugment: Maximizing the Utility of Speech Trans…

End-to-end speech translation (ST), which directly translates from source language speech into target language text, has attracted intensive attentions in recent years. Compared to conventional pipeline systems, end-to-end ST models have…

Neural Machine Translation (NMT) has been proven to achieve impressive results. The NMT system translation results depend strongly on the size and quality of parallel corpora. Nevertheless, for many language pairs, no rich-resource parallel…

Conventional spoken language understanding systems consist of two main components: an automatic speech recognition module that converts audio to a transcript, and a natural language understanding module that transforms the resulting text…

Data augmentation is an essential technique in natural language processing (NLP) for enriching training datasets by generating diverse samples. This process is crucial for improving the robustness and generalization capabilities of NLP…

Deep learning technologies have significantly advanced the performance of target speaker extraction (TSE) tasks. To enhance the generalization and robustness of these algorithms when training data is insufficient, data augmentation is a…

End-to-end approaches open a new way for more accurate and efficient spoken language understanding (SLU) systems by alleviating the drawbacks of traditional pipeline systems. Previous works exploit textual information for an SLU model via…

We introduce a novel setup for low-resource task-oriented semantic parsing which incorporates several constraints that may arise in real-world scenarios: (1) lack of similar datasets/models from a related domain, (2) inability to sample…

Text discourse parsing weighs importantly in understanding information flow and argumentative structure in natural language, making it beneficial for downstream tasks. While previous work significantly improves the performance of RST…

While speech recognition Word Error Rate (WER) has reached human parity for English, continuous speech recognition scenarios such as voice typing and meeting transcriptions still suffer from segmentation and punctuation problems, resulting…

Streaming speech translation (StreamST) requires determining appropriate timing, known as policy, to generate translations while continuously receiving source speech inputs, balancing low latency with high translation quality. However,…

Automatic speech recognition (ASR) for conversational code-switching speech remains challenging due to the scarcity of realistic, high-quality labeled speech data. This paper explores multilingual text-to-speech (TTS) models as an effective…

Simultaneous translation systems start producing the output while processing the partial source sentence in the incoming input stream. These systems need to decide when to read more input and when to write the output. These decisions depend…

Current research in speech-to-speech translation (S2ST) primarily concentrates on translation accuracy and speech naturalness, often overlooking key elements like paralinguistic information, which is essential for conveying emotions and…

Retrieval-based conversational systems learn to rank response candidates for a given dialogue context by computing the similarity between their vector representations. However, training on a single textual form of the multi-turn context…

End-to-end speech-to-speech (S2S) dialogue systems have recently garnered increasing research attention for their lower latency and more natural integration of nonverbal cues such as emotion and speaker identity. However, these systems face…

Data sparsity is a main problem hindering the development of code-switching (CS) NLP systems. In this paper, we investigate data augmentation techniques for synthesizing dialectal Arabic-English CS text. We perform lexical replacements…

Simultaneous machine translation (SiMT) is usually done via sequence-level knowledge distillation (Seq-KD) from a full-sentence neural machine translation (NMT) model. However, there is still a significant performance gap between NMT and…

Recent advancements in textless speech-to-speech translation systems have been driven by the adoption of self-supervised learning techniques. Although most state-of-the-art systems adopt a similar architecture to transform source language…

We introduces LLaST, a framework for building high-performance Large Language model based Speech-to-text Translation systems. We address the limitations of end-to-end speech translation(E2E ST) models by exploring model architecture design…

Speech Emotion Recognition (SER) is a crucial component in developing general-purpose AI agents capable of natural human-computer interaction. However, building robust multilingual SER systems remains challenging due to the scarcity of…