Related papers: Improving Speech-to-Speech Translation Through Unl…

Spoken language understanding (SLU) tasks involve diverse skills that probe the information extraction, classification and/or generation capabilities of models. In this setting, task-specific training data may not always be available. While…

Recently, very large language models (LLMs) have shown exceptional performance on several English NLP tasks with just in-context learning (ICL), but their utility in other languages is still underexplored. We investigate their effectiveness…

Recently, end-to-end multi-speaker text-to-speech (TTS) systems gain success in the situation where a lot of high-quality speech plus their corresponding transcriptions are available. However, laborious paired data collection processes…

Attention-based sequence-to-sequence modeling provides a powerful and elegant solution for applications that need to map one sequence to a different sequence. Its success heavily relies on the availability of large amounts of training data.…

Unsupervised pre-training is now the predominant approach for both text and speech understanding. Self-attention models pre-trained on large amounts of unannotated data have been hugely successful when fine-tuned on downstream tasks from a…

Neural text-to-speech (TTS) models can synthesize natural human speech when trained on large amounts of transcribed speech. However, collecting such large-scale transcribed data is expensive. This paper proposes an unsupervised pre-training…

Speech-to-speech translation combines machine translation with speech synthesis, introducing evaluation challenges not present in either task alone. How to automatically evaluate speech-to-speech translation is an open question which has…

Self-training has been shown to be helpful in addressing data scarcity for many domains, including vision, speech, and language. Specifically, self-training, or pseudo-labeling, labels unsupervised data and adds that to the training pool.…

Multimodal Large Language Models (MLLMs) have achieved notable success in enhancing translation performance by integrating multimodal information. However, existing research primarily focuses on image-guided methods, whose applicability is…

Speech-to-speech translation directly translates a speech utterance to another between different languages, and has great potential in tasks such as simultaneous interpretation. State-of-art models usually contains an auxiliary module for…

In this paper, we focus on improving the performance of the text-dependent speaker verification system in the scenario of limited training data. The speaker verification system deep learning based text-dependent generally needs a large…

We present a simple yet effective approach to build multilingual speech-to-text (ST) translation by efficient transfer learning from pretrained speech encoder and text decoder. Our key finding is that a minimalistic LNA (LayerNorm and…

This paper presents methods of making using of text supervision to improve the performance of sequence-to-sequence (seq2seq) voice conversion. Compared with conventional frame-to-frame voice conversion approaches, the seq2seq acoustic…

In recent years, Text-To-Speech (TTS) has been used as a data augmentation technique for speech recognition to help complement inadequacies in the training data. Correspondingly, we investigate the use of a multi-speaker TTS system to…

This study addresses the issue of speaker gender bias in Speech Translation (ST) systems, which can lead to offensive and inaccurate translations. The masculine bias often found in large-scale ST systems is typically perpetuated through…

This paper presents a method for selecting appropriate synthetic speech samples from a given large text-to-speech (TTS) dataset as supplementary training data for an automatic speech recognition (ASR) model. We trained a neural network,…

Simultaneous speech-to-text translation (Simul-S2TT) aims to translate speech into target text in real time, outputting translations while receiving source speech input, rather than waiting for the entire utterance to be spoken. Simul-S2TT…

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…

Simultaneous speech translation (SimulST) produces translations incrementally while processing partial speech input. Although large language models (LLMs) have showcased strong capabilities in offline translation tasks, applying them to…

This paper proposes a zero-shot text-to-speech (TTS) conditioned by a self-supervised speech-representation model acquired through self-supervised learning (SSL). Conventional methods with embedding vectors from x-vector or global style…