Related papers: Segmentation-Free Streaming Machine Translation

We adapt the well-known beam-search algorithm for machine translation to operate in a cascaded real-time speech translation system. This proved to be more complex than initially anticipated, due to four key challenges: (1) real-time…

Many machine translation toolkits make use of a data preparation step wherein raw data is transformed into a tensor format that can be used directly by the trainer. This preparation step is increasingly at odds with modern research and…

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…

This paper introduces a novel training framework called Focused Discriminative Training (FDT) to further improve streaming word-piece end-to-end (E2E) automatic speech recognition (ASR) models trained using either CTC or an interpolation of…

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…

Spoken language translation (SLT) has become very important in an increasingly globalized world. Machine translation (MT) for automatic speech recognition (ASR) systems is a major challenge of great interest. This research investigates that…

The growing need for instant spoken language transcription and translation is driven by increased global communication and cross-lingual interactions. This has made offering translations in multiple languages essential for user…

Speech segmentation, which splits long speech into short segments, is essential for speech translation (ST). Popular VAD tools like WebRTC VAD have generally relied on pause-based segmentation. Unfortunately, pauses in speech do not…

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…

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…

Automatic subtitling is the task of automatically translating the speech of audiovisual content into short pieces of timed text, i.e. subtitles and their corresponding timestamps. The generated subtitles need to conform to space and time…

Large-scale automatic speech translation systems today lack key features that help machine-mediated communication feel seamless when compared to human-to-human dialogue. In this work, we introduce a family of models that enable end-to-end…

Simultaneous translation of unbounded streaming speech remains a challenging problem due to the need for effectively processing the history speech context and past translations so that quality and latency, including computation overhead,…

Simultaneous speech translation (SST) takes streaming speech input and generates text translation on the fly. Existing methods either have high latency due to recomputation of input representations, or fall behind of offline ST in…

We propose a novel decoding approach for neural machine translation (NMT) based on continuous optimisation. We convert decoding - basically a discrete optimization problem - into a continuous optimization problem. The resulting constrained…

The increasing complexity of Industry 4.0 systems brings new challenges regarding predictive maintenance tasks such as fault detection and diagnosis. A corresponding and realistic setting includes multi-source data streams from different…

Direct speech-to-text translation (ST) models are usually trained on corpora segmented at sentence level, but at inference time they are commonly fed with audio split by a voice activity detector (VAD). Since VAD segmentation is not…

Machine translation systems are expected to cope with various types of constraints in many practical scenarios. While neural machine translation (NMT) has achieved strong performance in unconstrained cases, it is non-trivial to impose…

In this work, we focus on improving ASR output segmentation in the context of low-resource language speech-to-text translation. ASR output segmentation is crucial, as ASR systems segment the input audio using purely acoustic information and…

Machine Translation is one of the major oldest and the most active research area in Natural Language Processing. Currently, Statistical Machine Translation (SMT) dominates the Machine Translation research. Statistical Machine Translation is…