相关论文: Unit selection synthesis based data augmentation f…

Self-supervised learning of speech representations has achieved impressive results in improving automatic speech recognition (ASR). In this paper, we show that data selection is important for self-supervised learning. We propose a simple…

This study aims at designing an environment-aware text-to-speech (TTS) system that can generate speech to suit specific acoustic environments. It is also motivated by the desire to leverage massive data of speech audio from heterogeneous…

Whispering is a distinct form of speech known for its soft, breathy, and hushed characteristics, often used for private communication. The acoustic characteristics of whispered speech differ substantially from normally phonated speech and…

Automated speaking assessment (ASA) on opinion expressions is often hampered by the scarcity of labeled recordings, which restricts prompt diversity and undermines scoring reliability. To address this challenge, we propose a novel training…

Speaker diarization systems often struggle with high intrinsic intra-speaker variability, such as shifts in emotion, health, or content. This can cause segments from the same speaker to be misclassified as different individuals, for…

Despite the rapid growth in model architecture, the scarcity of large parallel corpora remains the main bottleneck in Neural Machine Translation. Data augmentation is a technique that enhances the performance of data-hungry models by…

Despite their empirical success, neural networks still have difficulty capturing compositional aspects of natural language. This work proposes a simple data augmentation approach to encourage compositional behavior in neural models for…

In low resource settings, data augmentation strategies are commonly leveraged to improve performance. Numerous approaches have attempted document-level augmentation (e.g., text classification), but few studies have explored token-level…

Data augmentation is an effective approach to tackle over-fitting. Many previous works have proposed different data augmentations strategies for NLP, such as noise injection, word replacement, back-translation etc. Though effective, they…

Collection of annotated dialogs for training task-oriented dialog systems have been one of the key bottlenecks in improving current models. While dialog response generation has been widely studied on the agent side, it is not evident if…

While automatic speech recognition (ASR) systems have achieved remarkable performance with large-scale datasets, their efficacy remains inadequate in low-resource settings, encompassing dialects, accents, minority languages, and long-tail…

High-fidelity speech can be synthesized by end-to-end text-to-speech models in recent years. However, accessing and controlling speech attributes such as speaker identity, prosody, and emotion in a text-to-speech system remains a challenge.…

Dialogue State Tracking (DST) is a key part of task-oriented dialogue systems, identifying important information in conversations. However, its accuracy drops significantly in spoken dialogue environments due to named entity errors from…

This paper proposes a unified deep speaker embedding framework for modeling speech data with different sampling rates. Considering the narrowband spectrogram as a sub-image of the wideband spectrogram, we tackle the joint modeling problem…

As it is cumbersome and expensive to acquire a huge amount of data for training neural dialog models, data augmentation is proposed to effectively utilize existing training samples. However, current data augmentation techniques on the…

Expressive speech synthesis requires vibrant prosody and well-timed pauses. We propose an effective strategy to augment a small dataset to train an expressive end-to-end Text-to-Speech model. We merge audios of emotionally congruent text…

Data augmentation has been an important ingredient for boosting performances of learned models. Prior data augmentation methods for few-shot text classification have led to great performance boosts. However, they have not been designed to…

The past decade has witnessed substantial growth of data-driven speech enhancement (SE) techniques thanks to deep learning. While existing approaches have shown impressive performance in some common datasets, most of them are designed only…

Training a code-switching end-to-end automatic speech recognition (ASR) model normally requires a large amount of data, while code-switching data is often limited. In this paper, three novel approaches are proposed for code-switching data…

There are two approaches for pairwise sentence scoring: Cross-encoders, which perform full-attention over the input pair, and Bi-encoders, which map each input independently to a dense vector space. While cross-encoders often achieve higher…