Fernando Villavicencio

The Voice Conversion Challenge 2016

This paper describes the Voice Conversion Challenge 2016 devised by the authors to better understand different voice conversion (VC) techniques by comparing their performance on a common dataset. The task of the challenge was speaker conversion, i.e., to transform the voice identity of a source speaker into that of a target speaker while preserving the linguistic content. Using a common dataset consisting of 162 utterances for training and 54 utterances for evaluation from each of 5 source and 5 target speakers, 17 groups working in VC around the world developed their own VC systems for every combination of the source and target speakers, i.e., 25 systems in total, and generated voice samples converted by the developed systems. These samples were evaluated in terms of target speaker similarity and naturalness by 200 listeners in a controlled environment. This paper summarizes the design of the challenge, its result, and a future plan to share views about unsolved problems and challenges faced by the current VC techniques.

Voice Liveness Detection for Speaker Verification based on a Tandem Single/Double-channel Pop Noise Detector.

This paper presents an algorithm for detecting spoofing attacks against automatic speaker verification (ASV) systems. While such systems now have performances comparable to those of other biometric modalities, spoofing techniques used against them have progressed drastically. Several techniques can be used to generate spoofing materials (e.g., speech synthesis and voice conversion techniques), and detecting them only on the basis of differences at an acoustic speaker modeling level is a challenging task. Moreover, differences between “live” and artificially generated material are expected to gradually decrease in the near future due to advances in synthesis technologies. A previously proposed “voice liveness” detection framework aimed at validating whether speech signals were generated by a person or artificially created uses elementary algorithms to detect pop noise. Detection is taken as evidence of liveness. A more advanced detection algorithm has now been developed that combines singleand double-channel pop noise detection. Experiments demonstrated that this tandem algorithm detects pop noise more effectively: the detection error rate was up to 80% less that those achieved with the elementary algorithms.

Observation-model error compensation for enhanced spectral envelope transformation in voice conversion

A strategy to enhance the signal quality and naturalness was designed for performing probabilistic spectral envelope transformation in voice conversion. The existing modeling error of the probabilistic mixture to represent the observed envelope features is translated generally as an averaging of the information in the spectral domain, resulting in over-smoothed spectra. Moreover, a transformation based on poorly modeled features might not be considered reliable. Our strategy consists of a novel definition of the spectral transformation to compensate the effect of both over-smoothing and poor modeling. The results of an experimental evaluation show that the perceived naturalness of converted speech was enhanced.

Development of a statistical parametric synthesis system for operatic singing in German

In this paper we describe the development of a Hidden Markov Model (HMM) based synthesis system for operatic singing in German, which is an extension of the HMM-based synthesis system for popular songs in Japanese and English called “Sinsy”. The implementation of this system consists of German text analysis, lexicon and Letter-To-Sound (LTS) conversion, and syllable duplication, which enables us to convert a German MusicXML input into context-dependent labels for acoustic modelling. Using the front-end, we develop two operatic singing voices, female mezzo-soprano and male bass voices, based on our new database, which consists of singing data of professional opera singers based in Vienna. We describe the details of the database and the recording procedure that is used to acquire singing data of four opera singers in German. For HMM training, we adopt a singer (speaker)-dependent training procedure. For duration modelling we propose a simple method that hierarchically constrains note durations by the overall utterance duration and then constrains phone durations by the synthesised note duration. We evaluate the performance of the voices with two vibrato modelling methods that have been proposed in the literature and show that HMM-based vibrato modelling can improve the overall quality.