Related papers: Simultaneous Translation for Unsegmented Input: A …

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…

While speech recognition Word Error Rate (WER) has reached human parity for English, long-form dictation scenarios still suffer from segmentation and punctuation problems resulting from irregular pausing patterns or slow speakers.…

Segmentation for continuous Automatic Speech Recognition (ASR) has traditionally used silence timeouts or voice activity detectors (VADs), which are both limited to acoustic features. This segmentation is often overly aggressive, given that…

The main aim of this paper is to investigate automatic quality assessment for spoken language translation (SLT). More precisely, we investigate SLT errors that can be due to transcription (ASR) or to translation (MT) modules. This paper…

In real-world applications, users often require both translations and transcriptions of speech to enhance their comprehension, particularly in streaming scenarios where incremental generation is necessary. This paper introduces a streaming…

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.…

Current simultaneous speech translation models can process audio only up to a few seconds long. Contemporary datasets provide an oracle segmentation into sentences based on human-annotated transcripts and translations. However, the…

The paper describes the BUT's speech translation systems. The systems are English$\longrightarrow$German offline speech translation systems. The systems are based on our previous works \cite{Jointly_trained_transformers}. Though End-to-End…

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…

We propose a method of segmenting long-form speech by separating semantically complete sentences within the utterance. This prevents the ASR decoder from needlessly processing faraway context while also preventing it from missing relevant…

We present a modular approach to building cascade speech translation (AST) models that guarantees that the resulting model performs no worse than the 1-best cascade baseline while preserving state-of-the-art speech recognition (ASR) and…

This paper addresses automatic quality assessment of spoken language translation (SLT). This relatively new task is defined and formalized as a sequence labeling problem where each word in the SLT hypothesis is tagged as good or bad…

We extend the frameworks of Serialized Output Training (SOT) to address practical needs of both streaming and offline automatic speech recognition (ASR) applications. Our approach focuses on balancing latency and accuracy, catering to…

This paper describes the cascaded multimodal speech translation systems developed by Imperial College London for the IWSLT 2019 evaluation campaign. The architecture consists of an automatic speech recognition (ASR) system followed by a…

In simultaneous machine translation, the objective is to determine when to produce a partial translation given a continuous stream of source words, with a trade-off between latency and quality. We propose a neural machine translation (NMT)…

This work proposes a grammar-based chunking strategy that segments input streams into semantically complete units by parsing dependency relations (e.g., noun phrase boundaries, verb-object structures) and punctuation features. The method…

Transfer learning from high-resource languages is known to be an efficient way to improve end-to-end automatic speech recognition (ASR) for low-resource languages. Pre-trained or jointly trained encoder-decoder models, however, do not share…

Encoder pre-training is promising in end-to-end Speech Translation (ST), given the fact that speech-to-translation data is scarce. But ST encoders are not simple instances of Automatic Speech Recognition (ASR) or Machine Translation (MT)…

For automatic speech translation (AST), end-to-end approaches are outperformed by cascaded models that transcribe with automatic speech recognition (ASR), then translate with machine translation (MT). A major cause of the performance gap is…

Simultaneous machine translation has recently gained traction thanks to significant quality improvements and the advent of streaming applications. Simultaneous translation systems need to find a trade-off between translation quality and…