相关论文: STEMM: Self-learning with Speech-text Manifold Mix…

Multilingual speech translation (ST) and machine translation (MT) in the medical domain enhances patient care by enabling efficient communication across language barriers, alleviating specialized workforce shortages, and facilitating…

End-to-end Speech Translation (ST) models have many potential advantages when compared to the cascade of Automatic Speech Recognition (ASR) and text Machine Translation (MT) models, including lowered inference latency and the avoidance of…

Modern automatic translation systems aim at place the human at the center by providing contextual support and knowledge. In this context, a critical task is enriching the output with information regarding the mentioned entities, which is…

This paper addresses the problem of simultaneous machine translation (SiMT) by exploring two main concepts: (a) adaptive policies to learn a good trade-off between high translation quality and low latency; and (b) visual information to…

Speech representation learning has improved both speech understanding and speech synthesis tasks for single language. However, its ability in cross-lingual scenarios has not been explored. In this paper, we extend the pretraining method for…

Recent advancements in speech-language models have yielded significant improvements in speech tokenization and synthesis. However, effectively mapping the complex, multidimensional attributes of speech into discrete tokens remains…

Streaming recognition and segmentation of multi-party conversations with overlapping speech is crucial for the next generation of voice assistant applications. In this work we address its challenges discovered in the previous work on…

Speech segmentation is an essential part of speech translation (ST) systems in real-world scenarios. Since most ST models are designed to process speech segments, long-form audio must be partitioned into shorter segments before translation.…

Expressive speech-to-speech translation (S2ST) is a key research topic in seamless communication, which focuses on the preservation of semantics and speaker vocal style in translated speech. Early works synthesized speaker style aligned…

With the rapid progress of speech language models (SLMs), discrete speech tokens have emerged as a core interface between speech and text, enabling unified modeling across modalities. Recent speech tokenization approaches aim to isolate…

The speech-to-singing (STS) voice conversion task aims to generate singing samples corresponding to speech recordings while facing a major challenge: the alignment between the target (singing) pitch contour and the source (speech) content…

In cross-lingual language understanding, machine translation is often utilized to enhance the transferability of models across languages, either by translating the training data from the source language to the target, or from the target to…

Aligning pretrained audio encoders and Large Language Models (LLMs) offers a promising, parameter-efficient path to building powerful multimodal agents. However, existing methods often require costly full-model finetuning or rely on static…

Simultaneous machine translation (SiMT) aims to translate a continuous input text stream into another language with the lowest latency and highest quality possible. The translation thus has to start with an incomplete source text, which is…

To let the state-of-the-art end-to-end ASR model enjoy data efficiency, as well as much more unpaired text data by multi-modal training, one needs to address two problems: 1) the synchronicity of feature sampling rates between speech and…

Multimodal representation learning has shown promising improvements on various vision-language tasks. Most existing methods excel at building global-level alignment between vision and language while lacking effective fine-grained image-text…

Multimodal sentiment analysis is a core research area that studies speaker sentiment expressed from the language, visual, and acoustic modalities. The central challenge in multimodal learning involves inferring joint representations that…

In this paper, we introduce a large model-empowered streaming semantic communication system for speech transmission across various languages, named LSSC-ST. Specifically, we devise an edge-device collaborative semantic communication…

End-to-end (E2E) speech-to-text translation (ST) often depends on pretraining its encoder and/or decoder using source transcripts via speech recognition or text translation tasks, without which translation performance drops substantially.…

Models for streaming speech translation (ST) can achieve high accuracy and low latency if they're developed with vast amounts of paired audio in the source language and written text in the target language. Yet, these text labels for the…