Related papers: On Target Segmentation for Direct Speech Translati…

Subword modeling for zero-resource languages aims to learn low-level representations of speech audio without using transcriptions or other resources from the target language (such as text corpora or pronunciation dictionaries). A good…

A sentence can be translated into more than one correct sentences. However, most of the existing neural machine translation models only use one of the correct translations as the targets, and the other correct sentences are punished as the…

In this research work, we perform text line segmentation directly in compressed representation of an unconstrained handwritten document image. In this relation, we make use of text line terminal points which is the current state-of-the-art.…

Machine transliteration is the process of automatically transforming the script of a word from a source language to a target language, while preserving pronunciation. Sequence to sequence learning has recently emerged as a new paradigm in…

Many self-supervised speech models (S3Ms) have been introduced over the last few years, improving performance and data efficiency on various speech tasks. However, these empirical successes alone do not give a complete picture of what is…

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…

Human talkers often address listeners with language-comprehension challenges, such as hard-of-hearing or non-native adults, by globally slowing down their speech. However, it remains unclear whether this strategy actually makes speech more…

Technical support problems are often long and complex. They typically contain user descriptions of the problem, the setup, and steps for attempted resolution. Often they also contain various non-natural language text elements like outputs…

Recent work on speech representation models jointly pre-trained with text has demonstrated the potential of improving speech representations by encoding speech and text in a shared space. In this paper, we leverage such shared…

Despite the remarkable advances in language modeling, current mainstream decoding methods still struggle to generate texts that align with human texts across different aspects. In particular, sampling-based methods produce less-repetitive…

Subtitling is becoming increasingly important for disseminating information, given the enormous amounts of audiovisual content becoming available daily. Although Neural Machine Translation (NMT) can speed up the process of translating…

Acoustic word embedding models map variable duration speech segments to fixed dimensional vectors, enabling efficient speech search and discovery. Previous work explored how embeddings can be obtained in zero-resource settings where no…

Monolingual data has been demonstrated to be helpful in improving the translation quality of neural machine translation (NMT). The current methods stay at the usage of word-level knowledge, such as generating synthetic parallel data or…

Direct speech-to-speech translation (S2ST) models suffer from data scarcity issues as there exists little parallel S2ST data, compared to the amount of data available for conventional cascaded systems that consist of automatic speech…

The purpose of speech tokenization is to transform a speech signal into a sequence of discrete representations, serving as the foundation for speech language models (SLMs). While speech tokenization has many options, their effect on the…

In this work, we provide a recipe for training machine translation models in a limited resource setting by leveraging synthetic target data generated using a large pre-trained model. We show that consistently across different benchmarks in…

Direct speech-to-speech translation (S2ST) is an attractive research topic with many advantages compared to cascaded S2ST. However, direct S2ST suffers from the data scarcity problem because the corpora from speech of the source language to…

When the amount of parallel sentences available to train a neural machine translation is scarce, a common practice is to generate new synthetic training samples from them. A number of approaches have been proposed to produce synthetic…

Dialogue segmentation is a crucial task for dialogue systems allowing a better understanding of conversational texts. Despite recent progress in unsupervised dialogue segmentation methods, their performances are limited by the lack of…

Representation learning is the foundation of machine reading comprehension. In state-of-the-art models, deep learning methods broadly use word and character level representations. However, character is not naturally the minimal linguistic…