Related papers: Using a Pitch-Synchronous Residual Codebook for Hy…

Parametric sound field synthesis methods, such as the Spatial Decomposition Method (SDM) and Higher-Order Spatial Impulse Response Rendering (HO-SIRR), are widely used for the analysis and auralization of sound fields. This paper studies…

In this paper, we propose a novel neural approach for paraphrase generation. Conventional para- phrase generation methods either leverage hand-written rules and thesauri-based alignments, or use statistical machine learning principles. To…

Acoustic matching aims to re-synthesize an audio clip to sound as if it were recorded in a target acoustic environment. Existing methods assume access to paired training data, where the audio is observed in both source and target…

In this paper, we introduce ConversaSynth, a framework designed to generate synthetic conversation audio using large language models (LLMs) with multiple persona settings. The framework first creates diverse and coherent text-based…

Supervised fine-tuning (SFT) is a common method to enhance the tool calling capabilities of Large Language Models (LLMs), with the training data often being synthesized. The current data synthesis process generally involves sampling a set…

The rapid growth of voice assistants powered by large language models (LLM) has highlighted a need for speech instruction data to train these systems. Despite the abundance of speech recognition data, there is a notable scarcity of speech…

The synthesis problem of static output feedback controllers within the anistropic-norm setup is revisited. A tractable synthesis approach involving iterations over a convex optimization problem is suggested, similarly to existing results…

A text-to-speech synthesis system typically consists of multiple stages, such as a text analysis frontend, an acoustic model and an audio synthesis module. Building these components often requires extensive domain expertise and may contain…

With the similarity between music and speech synthesis from symbolic input and the rapid development of text-to-speech (TTS) techniques, it is worthwhile to explore ways to improve the MIDI-to-audio performance by borrowing from TTS…

In speech recognition problems, data scarcity often poses an issue due to the willingness of humans to provide large amounts of data for learning and classification. In this work, we take a set of 5 spoken Harvard sentences from 7 subjects…

Various applications of voice synthesis have been developed independently despite the fact that they generate "voice" as output in common. In addition, the majority of voice synthesis models currently rely on annotated audio data, but it is…

In recent years, the introduction of neural networks (NNs) into the field of speech enhancement has brought significant improvements. However, many of the proposed methods are quite demanding in terms of computational complexity and memory…

This paper introduces a nonlinear string sound synthesizer, based on a finite difference simulation of the dynamic behavior of strings under various excitations. The presented synthesizer features a versatile string simulation engine…

Large language models (LLMs) have significantly advanced audio processing through audio codecs that convert audio into discrete tokens, enabling the application of language modeling techniques to audio data. However, audio codecs often…

Current status quo in machine learning is to use static datasets of real images for training, which often come from long-tailed distributions. With the recent advances in generative models, researchers have started augmenting these static…

Recently in statistical parametric speech synthesis, we proposed a continuous sinusoidal model (CSM) using continuous F0 (contF0) in combination with Maximum Voiced Frequency (MVF), which was successfully giving state-of-the-art vocoders…

This paper investigates the differences occuring in the excitation for different voice qualities. Its goal is two-fold. First a large corpus containing three voice qualities (modal, soft and loud) uttered by the same speaker is analyzed and…

In this paper, we propose a neural-based coding scheme in which an artificial neural network is exploited to automatically compress and decompress speech signals by a trainable approach. Having a two-stage training phase, the system can be…

Finding the right sound effects (SFX) to match moments in a video is a difficult and time-consuming task, and relies heavily on the quality and completeness of text metadata. Retrieving high-quality (HQ) SFX using a video frame directly as…

Embedding acoustic information into fixed length representations is of interest for a whole range of applications in speech and audio technology. Two novel unsupervised approaches to generate acoustic embeddings by modelling of acoustic…