No Arabic abstract
In this paper, we propose an online speaker adaptation method for WaveNet-based neural vocoders in order to improve their performance on speaker-independent waveform generation. In this method, a speaker encoder is first constructed using a large speaker-verification dataset which can extract a speaker embedding vector from an utterance pronounced by an arbitrary speaker. At the training stage, a speaker-aware WaveNet vocoder is then built using a multi-speaker dataset which adopts both acoustic feature sequences and speaker embedding vectors as conditions.At the generation stage, we first feed the acoustic feature sequence from a test speaker into the speaker encoder to obtain the speaker embedding vector of the utterance. Then, both the speaker embedding vector and acoustic features pass the speaker-aware WaveNet vocoder to reconstruct speech waveforms. Experimental results demonstrate that our method can achieve a better objective and subjective performance on reconstructing waveforms of unseen speakers than the conventional speaker-independent WaveNet vocoder.
We propose a linear prediction (LP)-based waveform generation method via WaveNet vocoding framework. A WaveNet-based neural vocoder has significantly improved the quality of parametric text-to-speech (TTS) systems. However, it is challenging to effectively train the neural vocoder when the target database contains massive amount of acoustical information such as prosody, style or expressiveness. As a solution, the approaches that only generate the vocal source component by a neural vocoder have been proposed. However, they tend to generate synthetic noise because the vocal source component is independently handled without considering the entire speech production process; where it is inevitable to come up with a mismatch between vocal source and vocal tract filter. To address this problem, we propose an LP-WaveNet vocoder, where the complicated interactions between vocal source and vocal tract components are jointly trained within a mixture density network-based WaveNet model. The experimental results verify that the proposed system outperforms the conventional WaveNet vocoders both objectively and subjectively. In particular, the proposed method achieves 4.47 MOS within the TTS framework.
Automatic speaker verification (ASV), one of the most important technology for biometric identification, has been widely adopted in security-critical applications, including transaction authentication and access control. However, previous work has shown that ASV is seriously vulnerable to recently emerged adversarial attacks, yet effective countermeasures against them are limited. In this paper, we adopt neural vocoders to spot adversarial samples for ASV. We use the neural vocoder to re-synthesize audio and find that the difference between the ASV scores for the original and re-synthesized audio is a good indicator for discrimination between genuine and adversarial samples. This effort is, to the best of our knowledge, among the first to pursue such a technical direction for detecting adversarial samples for ASV, and hence there is a lack of established baselines for comparison. Consequently, we implement the Griffin-Lim algorithm as the detection baseline. The proposed approach achieves effective detection performance that outperforms all the baselines in all the settings. We also show that the neural vocoder adopted in the detection framework is dataset-independent. Our codes will be made open-source for future works to do comparison.
We present a universal neural vocoder based on Parallel WaveNet, with an additional conditioning network called Audio Encoder. Our universal vocoder offers real-time high-quality speech synthesis on a wide range of use cases. We tested it on 43 internal speakers of diverse age and gender, speaking 20 languages in 17 unique styles, of which 7 voices and 5 styles were not exposed during training. We show that the proposed universal vocoder significantly outperforms speaker-dependent vocoders overall. We also show that the proposed vocoder outperforms several existing neural vocoder architectures in terms of naturalness and universality. These findings are consistent when we further test on more than 300 open-source voices.
In this paper we investigate the GMM-derived (GMMD) features for adaptation of deep neural network (DNN) acoustic models. The adaptation of the DNN trained on GMMD features is done through the maximum a posteriori (MAP) adaptation of the auxiliary GMM model used for GMMD feature extraction. We explore fusion of the adapted GMMD features with conventional features, such as bottleneck and MFCC features, in two different neural network architectures: DNN and time-delay neural network (TDNN). We analyze and compare different types of adaptation techniques such as i-vectors and feature-space adaptation techniques based on maximum likelihood linear regression (fMLLR) with the proposed adaptation approach, and explore their complementarity using various types of fusion such as feature level, posterior level, lattice level and others in order to discover the best possible way of combination. Experimental results on the TED-LIUM corpus show that the proposed adaptation technique can be effectively integrated into DNN and TDNN setups at different levels and provide additional gain in recognition performance: up to 6% of relative word error rate reduction (WERR) over the strong feature-space adaptation techniques based on maximum likelihood linear regression (fMLLR) speaker adapted DNN baseline, and up to 18% of relative WERR in comparison with a speaker independent (SI) DNN baseline model, trained on conventional features. For TDNN models the proposed approach achieves up to 26% of relative WERR in comparison with a SI baseline, and up 13% in comparison with the model adapted by using i-vectors. The analysis of the adapted GMMD features from various points of view demonstrates their effectiveness at different levels.
Emotional voice conversion (EVC) is one way to generate expressive synthetic speech. Previous approaches mainly focused on modeling one-to-one mapping, i.e., conversion from one emotional state to another emotional state, with Mel-cepstral vocoders. In this paper, we investigate building a multi-target EVC (MTEVC) architecture, which combines a deep bidirectional long-short term memory (DBLSTM)-based conversion model and a neural vocoder. Phonetic posteriorgrams (PPGs) containing rich linguistic information are incorporated into the conversion model as auxiliary input features, which boost the conversion performance. To leverage the advantages of the newly emerged neural vocoders, we investigate the conditional WaveNet and flow-based WaveNet (FloWaveNet) as speech generators. The vocoders take in additional speaker information and emotion information as auxiliary features and are trained with a multi-speaker and multi-emotion speech corpus. Objective metrics and subjective evaluation of the experimental results verify the efficacy of the proposed MTEVC architecture for EVC.