Related papers: Enhanced Direct Speech-to-Speech Translation Using…

Direct speech translation describes a scenario where only speech inputs and corresponding translations are available. Such data are notoriously limited. We present a technique that allows cascades of automatic speech recognition (ASR) and…

We present a bidirectional unsupervised model pre-training (UPT) method and apply it to children's automatic speech recognition (ASR). An obstacle to improving child ASR is the scarcity of child speech databases. A common approach to…

This paper presents an accented text-to-speech (TTS) synthesis framework with limited training data. We study two aspects concerning accent rendering: phonetic (phoneme difference) and prosodic (pitch pattern and phoneme duration)…

This work investigates a simple data augmentation technique, SpecAugment, for end-to-end speech translation. SpecAugment is a low-cost implementation method applied directly to the audio input features and it consists of masking blocks of…

This paper explores the instruction fine-tuning technique for speech-to-semantic tasks by introducing a unified end-to-end (E2E) framework that generates target text conditioned on a task-related prompt for audio data. We pre-train the…

We introduces LLaST, a framework for building high-performance Large Language model based Speech-to-text Translation systems. We address the limitations of end-to-end speech translation(E2E ST) models by exploring model architecture design…

Self-supervised Transformer based models, such as wav2vec 2.0 and HuBERT, have produced significant improvements over existing approaches to automatic speech recognition (ASR). This is evident in the performance of the wav2vec 2.0 based…

Recent advancements in end-to-end speech synthesis have made it possible to generate highly natural speech. However, training these models typically requires a large amount of high-fidelity speech data, and for unseen texts, the prosody of…

Language model pre-training has shown promising results in various downstream tasks. In this context, we introduce a cross-modal pre-trained language model, called Speech-Text BERT (ST-BERT), to tackle end-to-end spoken language…

Most previous neural text-to-speech (TTS) methods are mainly based on supervised learning methods, which means they depend on a large training dataset and hard to achieve comparable performance under low-resource conditions. To address this…

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…

Current self-supervised learning algorithms are often modality-specific and require large amounts of computational resources. To address these issues, we increase the training efficiency of data2vec, a learning objective that generalizes…

In this paper, we propose a weakly supervised multilingual representation learning framework, called cross-lingual self-training (XLST). XLST is able to utilize a small amount of annotated data from high-resource languages to improve the…

Data augmentation is one of the most effective ways to make end-to-end automatic speech recognition (ASR) perform close to the conventional hybrid approach, especially when dealing with low-resource tasks. Using recent advances in speech…

Training an end-to-end (E2E) neural network speech-to-intent (S2I) system that directly extracts intents from speech requires large amounts of intent-labeled speech data, which is time consuming and expensive to collect. Initializing the…

This paper presents Translatotron 3, a novel approach to unsupervised direct speech-to-speech translation from monolingual speech-text datasets by combining masked autoencoder, unsupervised embedding mapping, and back-translation.…

Multimodal Large Language Models (MLLMs) have achieved significant success in Speech-to-Text Translation (S2TT) tasks. While most existing research has focused on English-centric translation directions, the exploration of many-to-many…

Training personalized speech enhancement models is innately a no-shot learning problem due to privacy constraints and limited access to noise-free speech from the target user. If there is an abundance of unlabeled noisy speech from the…

We present a prosody-guided framework for speech-to-speech translation (S2ST) that aligns and translates speech \emph{without} transcripts by leveraging cross-linguistic pause synchrony. Analyzing a 6{,}000-hour East African news corpus…

Recently, neural networks based purely on self-attention, such as the Vision Transformer (ViT), have been shown to outperform deep learning models constructed with convolutional neural networks (CNNs) on various vision tasks, thus extending…