Related papers: Advancing Topic Segmentation of Broadcasted Speech…

Topic modeling is traditionally applied to word counts without accounting for the context in which words appear. Recent advancements in large language models (LLMs) offer contextualized word embeddings, which capture deeper meaning and…

Existing speech recognition systems are typically built at the sentence level, although it is known that dialog context, e.g. higher-level knowledge that spans across sentences or speakers, can help the processing of long conversations. The…

Recent efforts in Spoken Dialogue Modeling aim to synthesize spoken dialogue without the need for direct transcription, thereby preserving the wealth of non-textual information inherent in speech. However, this approach faces a challenge…

Weakly supervised semantic segmentation is a challenging task as it only takes image-level information as supervision for training but produces pixel-level predictions for testing. To address such a challenging task, most recent…

Deep neural network-based systems have significantly improved the performance of speaker diarization tasks. However, end-to-end neural diarization (EEND) systems often struggle to generalize to scenarios with an unseen number of speakers,…

Linear text segmentation is a long-standing problem in natural language processing (NLP), focused on dividing continuous text into coherent and semantically meaningful units. Despite its importance, the task remains challenging due to the…

This paper introduces a new statistical approach to partitioning text automatically into coherent segments. Our approach enlists both short-range and long-range language models to help it sniff out likely sites of topic changes in text. To…

Automatic speech transcripts are often delivered as unstructured word streams that impede readability and repurposing. We recast paragraph segmentation as the missing structuring step and fill three gaps at the intersection of speech…

Recently, end-to-end models have become a popular approach as an alternative to traditional hybrid models in automatic speech recognition (ASR). The multi-speaker speech separation and recognition task is a central task in cocktail party…

Text-to-speech (TTS) acoustic models map linguistic features into an acoustic representation out of which an audible waveform is generated. The latest and most natural TTS systems build a direct mapping between linguistic and waveform…

The ultimate goal of transfer learning is to reduce labeled data requirements by exploiting a pre-existing embedding model trained for different datasets or tasks. The visual and language communities have established benchmarks to compare…

Recently, attention-based transformers have become a de facto standard in many deep learning applications including natural language processing, computer vision, signal processing, etc.. In this paper, we propose a transformer-based…

Despite Telugu being spoken by over 80 million people, speech translation research for this morphologically rich language remains severely underexplored. We address this gap by developing a high-quality Telugu--English speech translation…

Multi-encoder models are a broad family of context-aware neural machine translation systems that aim to improve translation quality by encoding document-level contextual information alongside the current sentence. The context encoding is…

This paper presents a novel design of neural network system for fine-grained style modeling, transfer and prediction in expressive text-to-speech (TTS) synthesis. Fine-grained modeling is realized by extracting style embeddings from the…

Education systems are dynamically changing to accommodate technological advances, industrial and societal needs, and to enhance students' learning journeys. Curriculum specialists and educators constantly revise taught subjects across…

In this work, we showcase a cost-effective method for generating training data for speech processing tasks. First, we transcribe unlabeled speech using a state-of-the-art Automatic Speech Recognition (ASR) model. Next, we align generated…

Dialogue topic segmentation is critical in several dialogue modeling problems. However, popular unsupervised approaches only exploit surface features in assessing topical coherence among utterances. In this work, we address this limitation…

In this paper, we address the task of spoken language understanding. We present a method for translating spoken sentences from one language into spoken sentences in another language. Given spectrogram-spectrogram pairs, our model can be…

Language models (LMs) have shown superior performances in various speech generation tasks recently, demonstrating their powerful ability for semantic context modeling. Given the intrinsic similarity between speech generation and speech…