Related papers: PsFuture: A Pseudo-Future-based Zero-Shot Adaptive…
We present a new approach to perform zero-shot cross-modal transfer between speech and text for translation tasks. Multilingual speech and text are encoded in a joint fixed-size representation space. Then, we compare different approaches to…
Zero-shot streaming text-to-speech is an important research topic in human-computer interaction. Existing methods primarily use a lookahead mechanism, relying on future text to achieve natural streaming speech synthesis, which introduces…
Many robotic applications require the agent to perform long-horizon tasks in partially observable environments. In such applications, decision making at any step can depend on observations received far in the past. Hence, being able to…
A popular approach to streaming speech translation is to employ a single offline model with a wait-k policy to support different latency requirements, which is simpler than training multiple online models with different latency constraints.…
Simultaneous speech translation (SimulST) translates partial speech inputs incrementally. Although the monotonic correspondence between input and output is preferable for smaller latency, it is not the case for distant language pairs such…
Simultaneous translation involves translating a sentence before the speaker's utterance is completed in order to realize real-time understanding in multiple languages. This task is significantly more challenging than the general full…
Multilingual Neural Machine Translation (MNMT) enables one system to translate sentences from multiple source languages to multiple target languages, greatly reducing deployment costs compared with conventional bilingual systems. The MNMT…
Speech-to-text translation (ST), which translates source language speech into target language text, has attracted intensive attention in recent years. Compared to the traditional pipeline system, the end-to-end ST model has potential…
Tabular Foundation Models (TFMs) have recently shown strong in-context learning capabilities on structured data, achieving zero-shot performance comparable to traditional machine learning methods. We find that zero-shot TFMs already achieve…
Simultaneous Machine Translation (SiMT) aims to yield a real-time partial translation with a monotonically growing the source-side context. However, there is a counterintuitive phenomenon about the context usage between training and…
There has been significant progress in open-source text-only translation large language models (LLMs) with better language coverage and quality. However, these models can be only used in cascaded pipelines for speech translation (ST),…
We use model-free reinforcement learning, extensive simulation, and transfer learning to develop a continuous control algorithm that has good zero-shot performance in a real physical environment. We train a simulated agent to act optimally…
Speech editing and zero-shot Text-to-Speech (TTS) share a similar generative foundation conditioned on speech prompts, yet speech editing demands far stricter local acoustic consistency with surrounding unedited content. While prior work…
Current end-to-end approaches to Spoken Language Translation (SLT) rely on limited training resources, especially for multilingual settings. On the other hand, Multilingual Neural Machine Translation (MultiNMT) approaches rely on…
Recently, data-driven task-oriented dialogue systems have achieved promising performance in English. However, developing dialogue systems that support low-resource languages remains a long-standing challenge due to the absence of…
Recent few-shot methods, such as parameter-efficient fine-tuning (PEFT) and pattern exploiting training (PET), have achieved impressive results in label-scarce settings. However, they are difficult to employ since they are subject to high…
The primary objective of simultaneous machine translation (SiMT) is to minimize latency while preserving the quality of the final translation. Drawing inspiration from CPU branch prediction techniques, we propose incorporating branch…
An important concern in training multilingual neural machine translation (NMT) is to translate between language pairs unseen during training, i.e zero-shot translation. Improving this ability kills two birds with one stone by providing an…
There has been great progress in improving streaming machine translation, a simultaneous paradigm where the system appends to a growing hypothesis as more source content becomes available. We study a related problem in which revisions to…
Machine Translation (MT) is usually viewed as a one-shot process that generates the target language equivalent of some source text from scratch. We consider here a more general setting which assumes an initial target sequence, that must be…