Related papers: Utilizing TTS Synthesized Data for Efficient Devel…
Personalized TTS is an exciting and highly desired application that allows users to train their TTS voice using only a few recordings. However, TTS training typically requires many hours of recording and a large model, making it unsuitable…
While modern Text-to-Speech (TTS) systems can produce natural-sounding speech, they remain unable to reproduce the full diversity found in natural speech data. We consider the distribution of all possible real speech samples that could be…
Knowledge Tracing (KT) aims to predict the future performance of students by tracking the development of their knowledge states. Despite all the recent progress made in this field, the application of KT models in education systems is still…
Customized keyword spotting (KWS) has great potential to be deployed on edge devices to achieve hands-free user experience. However, in real applications, false alarm (FA) would be a serious problem for spotting dozens or even hundreds of…
Most of the existing neural-based models for keyword spotting (KWS) in smart devices require thousands of training samples to learn a decent audio representation. However, with the rising demand for smart devices to become more…
The zero-shot text-to-speech (TTS) method, based on speaker embeddings extracted from reference speech using self-supervised learning (SSL) speech representations, can reproduce speaker characteristics very accurately. However, this…
Smart audio devices are gated by an always-on lightweight keyword spotting program to reduce power consumption. It is however challenging to design models that have both high accuracy and low latency for accurate and fast responsiveness.…
Creating realistic and natural-sounding synthetic speech remains a big challenge for voice identities unseen during training. As there is growing interest in synthesizing voices of new speakers, here we investigate the ability of…
In this paper, we present a new objective prediction model for synthetic speech naturalness. It can be used to evaluate Text-To-Speech or Voice Conversion systems and works language independently. The model is trained end-to-end and based…
Adapting generic speech recognition models to specific individuals is a challenging problem due to the scarcity of personalized data. Recent works have proposed boosting the amount of training data using personalized text-to-speech…
This paper introduces a new multi-speaker English dataset for training text-to-speech models. The dataset is based on LibriVox audiobooks and Project Gutenberg texts, both in the public domain. The new dataset contains about 292 hours of…
In order to maximize detection precision rate as well as the recall rate, this paper proposes an in-vehicle multi-source fusion scheme in Keyword Spotting (KWS) System for vehicle applications. Vehicle information, as a new source for the…
High-quality and intelligible speech is essential to text-to-speech (TTS) model training, however, obtaining high-quality data for low-resource languages is challenging and expensive. Applying speech enhancement on Automatic Speech…
Text-to-speech (TTS) synthesis is a technology that converts written text into spoken words, enabling a natural and accessible means of communication. This abstract explores the key aspects of TTS synthesis, encompassing its underlying…
Despite their great performance over the years, handcrafted speech features are not necessarily optimal for any particular speech application. Consequently, with greater or lesser success, optimal filterbank learning has been studied for…
In recent years, speech generation has seen remarkable progress, now achieving one-shot generation capability that is often virtually indistinguishable from real human voice. Integrating such advancements in speech generation with large…
Zero-shot Text-To-Speech (TTS) synthesis shows great promise for personalized voice customization through voice cloning. However, current methods for achieving zero-shot TTS heavily rely on large model scales and extensive training datasets…
Synthetic data is a standard component in training large language models, yet systematic comparisons across design dimensions, including rephrasing strategy, generator model, and source data, remain absent. We conduct extensive controlled…
End-to-end models are an attractive new approach to spoken language understanding (SLU) in which the meaning of an utterance is inferred directly from the raw audio without employing the standard pipeline composed of a separately trained…
Keyword spotting (KWS) has become an indispensable part of many intelligent devices surrounding us, as audio is one of the most efficient ways of interacting with these devices. The accuracy and performance of KWS solutions have been the…