Skip to search formSkip to main contentSkip to account menu

ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech

View via Publisher (opens in a new tab)

A Comparison of Recent Waveform Generation and Acoustic Modeling Methods for Neural-Network-Based Speech Synthesis

This paper builds a framework in which new vocoding and acoustic modeling techniques with conventional approaches are compared by means of a large scale crowdsourced evaluation, and shows that generative adversarial networks and an autoregressive (AR) model performed better than a normal recurrent network and the AR model performed best.
View on IEEE (opens in a new tab)

Real-Time Modeling of Audio Distortion Circuits with Deep Learning

The deep neural network studied in this work is useful for real-time virtual analog modeling of nonlinear audio circuits and can be run in real time on a desktop computer.

Non-parallel voice conversion using i-vector PLDA: towards unifying speaker verification and transformation

This work adopts probabilistic linear discriminant analysis (PLDA) for voice conversion and adopts i-vector method to voice conversion, which requires neither parallel utterances, transcriptions nor time alignment procedures at any stage.
View on IEEE (opens in a new tab)

Real-Time Guitar Amplifier Emulation with Deep Learning

It is demonstrated that the neural network models can convincingly emulate highly nonlinear audio distortion circuits, whilst running in real-time, with some models requiring only a relatively small amount of processing power to run on a modern desktop computer.
View PDF (opens in a new tab)

GlottDNN - A Full-Band Glottal Vocoder for Statistical Parametric Speech Synthesis

The proposed GlottDNN vocoder was evaluated as part of a full-band state-of-the-art DNN-based text-to-speech (TTS) synthesis system and compared against the release version of the original GlottHMM vocoder, and the well-known STRAIGHT vocoder.
View via Publisher (opens in a new tab)

Speaking Style Conversion from Normal to Lombard Speech Using a Glottal Vocoder and Bayesian GMMs

A parametric approach that uses a vocoder to extract speech features from utterances spoken in normal style to the corresponding features of Lombard speech, and shows that the system is able to convert normal speech into Lombardspeech for the two vocoders.
View via Publisher (opens in a new tab)

A Comparison Between STRAIGHT, Glottal, and Sinusoidal Vocoding in Statistical Parametric Speech Synthesis

The obtained results suggest that the choice of the voice has a profound impact on the overall quality of the vocoder-generated speech, and the best vocoder for each voice can vary case by case, indicating that the waveform generation method of a vocoder is essential for quality improvements.
View on ACM (opens in a new tab)

Speaker-independent raw waveform model for glottal excitation

A multi-speaker 'GlotNet' vocoder, which utilizes a WaveNet to generate glottal excitation waveforms, which are then used to excite the corresponding vocal tract filter to produce speech.
View PDF on arXiv (opens in a new tab)

Deep Learning for Tube Amplifier Emulation

This work proposes a generic data-driven approach to virtual analog modeling and applies it to the Fender Bassman 56F-A vacuum-tube amplifier, and faithfully restitutes the range of sonic characteristics found across the configurations of the original device.
View on IEEE (opens in a new tab)
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)