Related papers: Standard-to-Dialect Transfer Trends Differ across …

Accent Conversion (AC) seeks to change the accent of speech from one (source) to another (target) while preserving the speech content and speaker identity. However, many AC approaches rely on source-target parallel speech data. We propose a…

Text style transfer involves rewriting the content of a source sentence in a target style. Despite there being a number of style tasks with available data, there has been limited systematic discussion of how text style datasets relate to…

Text-to-speech systems recently achieved almost indistinguishable quality from human speech. However, the prosody of those systems is generally flatter than natural speech, producing samples with low expressiveness. Disentanglement of…

Style transfer has been widely explored in natural language generation with non-parallel corpus by directly or indirectly extracting a notion of style from source and target domain corpus. A common shortcoming of existing approaches is the…

Speech-to-speech translation (S2ST) aims to convert spoken input in one language to spoken output in another, typically focusing on either language translation or accent adaptation. However, effective cross-cultural communication requires…

Transfer learning is an exciting area of Natural Language Processing that has the potential to both improve model performance and increase data efficiency. This study explores the effects of varying quantities of target task training data…

Textless speech-to-speech translation systems are rapidly advancing, thanks to the integration of self-supervised learning techniques. However, existing state-of-the-art systems fall short when it comes to capturing and transferring…

We present a neural text-to-speech system for fine-grained prosody transfer from one speaker to another. Conventional approaches for end-to-end prosody transfer typically use either fixed-dimensional or variable-length prosody embedding via…

This paper proposes a first attempt to build an end-to-end speech-to-text translation system, which does not use source language transcription during learning or decoding. We propose a model for direct speech-to-text translation, which…

Speech language models refer to language models with speech processing and understanding capabilities. One key desirable capability for speech language models is the ability to capture the intricate interdependency between content and…

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…

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…

The paper describes BUT's English to German offline speech translation(ST) systems developed for IWSLT2021. They are based on jointly trained Automatic Speech Recognition-Machine Translation models. Their performances is evaluated on…

We introduce a text-to-speech(TTS) framework based on a neural transducer. We use discretized semantic tokens acquired from wav2vec2.0 embeddings, which makes it easy to adopt a neural transducer for the TTS framework enjoying its monotonic…

Discourse analysis allows us to attain inferences of a text document that extend beyond the sentence-level. The current performance of discourse models is very low on texts outside of the training distribution's coverage, diminishing the…

There has been increasing interest in building multilingual foundation models for NLP and speech research. This paper examines how to expand the speech translation capability of these models with restricted data. Whisper, a speech…

For many text classification tasks, there is a major problem posed by the lack of labeled data in a target domain. Although classifiers for a target domain can be trained on labeled text data from a related source domain, the accuracy of…

End-to-end intent classification using speech has numerous advantages compared to the conventional pipeline approach using automatic speech recognition (ASR), followed by natural language processing modules. It attempts to predict intent…

Traditionally, large language models have been either trained on general web crawls or domain-specific data. However, recent successes of generative large language models, have shed light on the benefits of cross-domain datasets. To examine…

In this work, we studied the synthesis of Swiss German speech using different Text-to-Speech (TTS) models. We evaluated the TTS models on three corpora, and we found, that VITS models performed best, hence, using them for further testing.…