Related papers: pch2csd: an application for converting Nord Modula…
Modulations are a critical part of sound design and music production, enabling the creation of complex and evolving audio. Modern synthesizers provide envelopes, low frequency oscillators (LFOs), and more parameter automation tools that…
Submodular functions have many applications. Matchings have many applications. The bitext word alignment problem can be modeled as the problem of maximizing a nonnegative, monotone, submodular function constrained to matchings in a complete…
Neural audio codecs are initially introduced to compress audio data into compact codes to reduce transmission latency. Researchers recently discovered the potential of codecs as suitable tokenizers for converting continuous audio into…
Component-based development (CBD) is a name, with which software development professionals are quite familiar. There are several models which have been proposed for CBD in last few years. They contain good features but there are some…
Encouraged by recent interest in traditional Chinese instruments this work proposes a computational sound synthesis model for a traditional Chinese instrument, the guzheng. Digital waveguide model and modal synthesis are the most popular…
This paper advances the design of CTC-based all-neural (or end-to-end) speech recognizers. We propose a novel symbol inventory, and a novel iterated-CTC method in which a second system is used to transform a noisy initial output into a…
Code-switching is a data augmentation scheme mixing words from multiple languages into source lingual text. It has achieved considerable generalization performance of cross-lingual transfer tasks by aligning cross-lingual contextual word…
Synthesizer is a type of electronic musical instrument that is now widely used in modern music production and sound design. Each parameters configuration of a synthesizer produces a unique timbre and can be viewed as a unique instrument.…
Neural codecs have demonstrated strong performance in high-fidelity compression of audio signals at low bitrates. The token-based representations produced by these codecs have proven particularly useful for generative modeling. While much…
Modifying the pitch and timing of an audio signal are fundamental audio editing operations with applications in speech manipulation, audio-visual synchronization, and singing voice editing and synthesis. Thus far, methods for pitch-shifting…
Utterances by L2 speakers can be unintelligible due to mispronunciation and improper prosody. In computer-aided language learning systems, textual feedback is often provided using a speech recognition engine. However, an ideal form of…
In view of the High Luminosity LHC, the current CMS tracking detector will have to be replaced during Long Shutdown 3 to cope with the higher radiation environment and to withstand an increased data rate. To prepare for the so-called CMS…
Recently, sequence-to-sequence (seq-to-seq) models have been successfully applied in text-to-speech (TTS) to synthesize speech for single-language text. To synthesize speech for multiple languages usually requires multi-lingual speech from…
This paper describes an experimental system designed for development of real time voice synthesis applications. The system is composed from a DSP coprocessor card, equipped with an TMS320C25 or TMS320C50 chip, voice acquisition module…
We construct modular invariant partition functions for strings propagating on non-compact manifolds of G_2 holonomy. Our amplitudes involve a pair of N=1 minimal models M_m, M_{m+2} (m=3,4,...) and are identified as describing strings on…
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…
P300 is an Event-Related Potential widely used in Brain-Computer Interfaces, but its detection is challenging due to inter-subject and temporal variability. This work introduces a clustering methodology based on Normalized Compression…
The premise of this article is that a basic understanding of the composition and functioning of large language models is critically urgent. To that end, we extract a representational map of OpenAI's GPT-2 with what we articulate as two…
Audio synthesis has broad applications in multimedia. Recent advancements have made it possible to generate relevant audios from inputs describing an audio scene, such as images or texts. However, the immersiveness and expressiveness of the…
Deep learning models require large amounts of clean data to acheive good performance. To avoid the cost of expensive data acquisition, researchers use the abundant data available on the internet. This raises significant privacy concerns on…