A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
WeSinger improves singing voice synthesis with data augmentation and specialized modules.
A fast voice conversion method using diffusion models.
Speech Translation has always been about giving source text or audio input and waiting for system to give translated output in desired form. In this paper, we present the Acoustic Dialect Decoder (ADD) - a voice to voice ear-piece translation device. We introduce and survey the recent advances made in the field of Spee…
Inspired by recent work on neural network image generation which rely on backpropagation towards the network inputs, we present a proof-of-concept system for speech texture synthesis and voice conversion based on two mechanisms: approximate inversion of the representation learned by a speech recognition neural network,…
Deep learning converts one singer's voice to another without supervision.
This paper converts speech to match a face image and vice versa.
Paper uses SSL models' uncertainty to predict audio quality efficiently.
Thanks to the growing availability of spoofing databases and rapid advances in using them, systems for detecting voice spoofing attacks are becoming more and more capable, and error rates close to zero are being reached for the ASVspoof2015 database. However, speech synthesis and voice conversion paradigms that are not…
This paper proposes a new architecture for speaker adaptation of multi-speaker neural-network speech synthesis systems, in which an unseen speaker's voice can be built using a relatively small amount of speech data without transcriptions. This is sometimes called "unsupervised speaker adaptation". More specifically, we…
This paper describes a method based on a sequence-to-sequence learning (Seq2Seq) with attention and context preservation mechanism for voice conversion (VC) tasks. Seq2Seq has been outstanding at numerous tasks involving sequence modeling such as speech synthesis and recognition, machine translation, and image captioni…
Joint training model for TTS and VC tasks using Tacotron and WaveNet.
This paper proposes a method for generating speech from filterbank mel frequency cepstral coefficients (MFCC), which are widely used in speech applications, such as ASR, but are generally considered unusable for speech synthesis. First, we predict fundamental frequency and voicing information from MFCCs with an autoreg…
Although voice conversion (VC) algorithms have achieved remarkable success along with the development of machine learning, superior performance is still difficult to achieve when using nonparallel data. In this paper, we propose using a cycle-consistent adversarial network (CycleGAN) for nonparallel data-based VC train…
Improved human-like speech synthesis using WaveGAN extensions.
The state-of-the-art in text-to-speech synthesis has recently improved considerably due to novel neural waveform generation methods, such as WaveNet. However, these methods suffer from their slow sequential inference process, while their parallel versions are difficult to train and even more expensive computationally. …
VPFD uses vocoder features for adversarial training in VC.
The paper discovers a hidden component in data using an autoencoder with a discriminator.
Enhanced text-to-speech synthesizes expressive speech from a single example.
Unsupervised model generates distinct intonation codes for speech synthesis.
In this paper, we propose a dictionary update method for Nonnegative Matrix Factorization (NMF) with high dimensional data in a spectral conversion (SC) task. Voice conversion has been widely studied due to its potential applications such as personalized speech synthesis and speech enhancement. Exemplar-based NMF (ENMF…
Paper proposes singing voice conversion without parallel data.
iSTFTNet speeds up mel-spectrogram vocoders without sacrificing quality.
Solution for voice conversion with limited data using hierarchical seq2seq and attention models.
This research investigates the Statistical Machine Translation approaches to translate speech in real time automatically. Such systems can be used in a pipeline with speech recognition and synthesis software in order to produce a real-time voice communication system between foreigners. We obtained three main data sets …
Convolutional network converts speaker voices without text.
End-to-end voice conversion without vocoder.
Improved voice conversion with semi-supervised learning.
One-shot VC model converts voices without parallel data.
AUTOVC converts voices without parallel data, achieving state-of-the-art results.
New method separates multiple voices in mixed audio.
A new neural network separates singing voices more effectively.
Improved U-Nets with various intermediate blocks enhance singing voice separation.
Privacy-preserving method protects user speech data from cloud services.
Wave-U-Net with MHE regularization improves singing voice separation.
Automatic voice-controlled systems have changed the way humans interact with a computer. Voice or speech recognition systems allow a user to make a hands-free request to the computer, which in turn processes the request and serves the user with appropriate responses. After years of research and developments in machine …
Automated detection of voice disorders with computational methods is a recent research area in the medical domain since it requires a rigorous endoscopy for the accurate diagnosis. Efficient screening methods are required for the diagnosis of voice disorders so as to provide timely medical facilities in minimal resourc…
Recent speech technology research has seen a growing interest in using WaveNets as statistical vocoders, i.e., generating speech waveforms from acoustic features. These models have been shown to improve the generated speech quality over classical vocoders in many tasks, such as text-to-speech synthesis and voice conver…
Improved autoencoder for F0-consistent voice conversion.
Proposes a new voice conversion model that preserves pitch patterns.
Blow converts non-parallel raw audio voices efficiently.
We study the problem of semi-supervised singing voice separation, in which the training data contains a set of samples of mixed music (singing and instrumental) and an unmatched set of instrumental music. Our solution employs a single mapping function g, which, applied to a mixed sample, recovers the underlying instrum…
Many people are suffering from voice disorders, which can adversely affect the quality of their lives. In response, some researchers have proposed algorithms for automatic assessment of these disorders, based on voice signals. However, these signals can be sensitive to the recording devices. Indeed, the channel effect …
Improved speech recognition for voice assistants by analyzing speech data.
This paper introduces a novel recurrent model for music composition that is tailored to the structure of polyphonic music. We propose an efficient new conditional probabilistic factorization of musical scores, viewing a score as a collection of concurrent, coupled sequences: i.e. voices. To model the conditional distri…
Many-to-Many VTN improves voice conversion across multiple speakers.
Study improves voice conversion model with Mel-spectrogram augmentation.
Dr.VOT measures both positive and negative VOTs accurately in natural speech.
Personal VAD detects target speaker voice activity efficiently.