Electrical Engineering And Systems Science

Sequence-to-sequence (seq2seq) voice conversion (VC) models are attractive owing to their ability to convert prosody. Nonetheless, without sufficient data, seq2seq VC models can suffer from unstable training and mispronunciation problems in the converted speech, thus far from practical. To tackle these shortcomings, we propose to transfer knowledge from other speech processing tasks where large-scale corpora are easily available, typically text-to-speech (TTS) and automatic speech recognition (ASR). We argue that VC models initialized with such pretrained ASR or TTS model parameters can generate effective hidden representations for high-fidelity, highly intelligible converted speech. We apply such techniques to recurrent neural network (RNN)-based and Transformer based models, and through systematical experiments, we demonstrate the effectiveness of the pretraining scheme and the superiority of Transformer based models over RNN-based models in terms of intelligibility, naturalness, and similarity.

Voice User Interfaces (VUIs) are increasingly popular and built into smartphones, home assistants, and Internet of Things (IoT) devices. Despite offering an always-on convenient user experience, VUIs raise new security and privacy concerns for their users. In this paper, we focus on attribute inference attacks in the speech domain, demonstrating the potential for an attacker to accurately infer a target user's sensitive and private attributes (e.g. their emotion, sex, or health status) from deep acoustic models. To defend against this class of attacks, we design, implement, and evaluate a user-configurable, privacy-aware framework for optimizing speech-related data sharing mechanisms. Our objective is to enable primary tasks such as speech recognition and user identification, while removing sensitive attributes in the raw speech data before sharing it with a cloud service provider. We leverage disentangled representation learning to explicitly learn independent factors in the raw data. Based on a user's preferences, a supervision signal informs the filtering out of invariant factors while retaining the factors reflected in the selected preference. Our experimental evaluation over five datasets shows that the proposed framework can effectively defend against attribute inference attacks by reducing their success rates to approximately that of guessing at random, while maintaining accuracy in excess of 99% for the tasks of interest. We conclude that negotiable privacy settings enabled by disentangled representations can bring new opportunities for privacy-preserving applications.

Recent neural speech synthesis systems have gradually focused on the control of prosody to improve the quality of synthesized speech, but they rarely consider the variability of prosody and the correlation between prosody and semantics together. In this paper, a prosody learning mechanism is proposed to model the prosody of speech based on TTS system, where the prosody information of speech is extracted from the melspectrum by a prosody learner and combined with the phoneme sequence to reconstruct the mel-spectrum. Meanwhile, the sematic features of text from the pre-trained language model is introduced to improve the prosody prediction results. In addition, a novel self-attention structure, named as local attention, is proposed to lift this restriction of input text length, where the relative position information of the sequence is modeled by the relative position matrices so that the position encodings is no longer needed. Experiments on English and Mandarin show that speech with more satisfactory prosody has obtained in our model. Especially in Mandarin synthesis, our proposed model outperforms baseline model with a MOS gap of 0.08, and the overall naturalness of the synthesized speech has been significantly improved.

In speech production research, different imaging modalities have been employed to obtain accurate information about the movement and shaping of the vocal tract. Ultrasound is an affordable and non-invasive imaging modality with relatively high temporal and spatial resolution to study the dynamic behavior of tongue during speech production. However, a long-standing problem for ultrasound tongue imaging is the transducer misalignment during longer data recording sessions. In this paper, we propose a simple, yet effective, misalignment quantification approach. The analysis employs MSE distance and two similarity measurement metrics to identify the relative displacement between the chin and the transducer. We visualize these measures as a function of the timestamp of the utterances. Extensive experiments are conducted on a Hungarian and Scottish English child dataset. The results suggest that large values of Mean Square Error (MSE) and small values of Structural Similarity Index (SSIM) and Complex Wavelet SSIM indicate corruptions or issues during the data recordings, which can either be caused by transducer misalignment or lack of gel.

In this paper, we propose a quasi-periodic parallel WaveGAN (QPPWG) waveform generative model, which applies a quasi-periodic (QP) structure to a parallel WaveGAN (PWG) model using pitch-dependent dilated convolution networks (PDCNNs). PWG is a small-footprint GAN-based raw waveform generative model, whose generation time is much faster than real time because of its compact model and non-autoregressive (non-AR) and non-causal mechanisms. Although PWG achieves high-fidelity speech generation, the generic and simple network architecture lacks pitch controllability for an unseen auxiliary fundamental frequency ( F 0 ) feature such as a scaled F 0 . To improve the pitch controllability and speech modeling capability, we apply a QP structure with PDCNNs to PWG, which introduces pitch information to the network by dynamically changing the network architecture corresponding to the auxiliary F 0 feature. Both objective and subjective experimental results show that QPPWG outperforms PWG when the auxiliary F 0 feature is scaled. Moreover, analyses of the intermediate outputs of QPPWG also show better tractability and interpretability of QPPWG, which respectively models spectral and excitation-like signals using the cascaded fixed and adaptive blocks of the QP structure.

In this paper, a pitch-adaptive waveform generative model named Quasi-Periodic WaveNet (QPNet) is proposed to improve the limited pitch controllability of vanilla WaveNet (WN) using pitch-dependent dilated convolution neural networks (PDCNNs). Specifically, as a probabilistic autoregressive generation model with stacked dilated convolution layers, WN achieves high-fidelity audio waveform generation. However, the pure-data-driven nature and the lack of prior knowledge of audio signals degrade the pitch controllability of WN. For instance, it is difficult for WN to precisely generate the periodic components of audio signals when the given auxiliary fundamental frequency ( F 0 ) features are outside the F 0 range observed in the training data. To address this problem, QPNet with two novel designs is proposed. First, the PDCNN component is applied to dynamically change the network architecture of WN according to the given auxiliary F 0 features. Second, a cascaded network structure is utilized to simultaneously model the long- and short-term dependencies of quasi-periodic signals such as speech. The performances of single-tone sinusoid and speech generations are evaluated. The experimental results show the effectiveness of the PDCNNs for unseen auxiliary F 0 features and the effectiveness of the cascaded structure for speech generation.

Deep learning enables the development of efficient end-to-end speech processing applications while bypassing the need for expert linguistic and signal processing features. Yet, recent studies show that good quality speech resources and phonetic transcription of the training data can enhance the results of these applications. In this paper, the RECOApy tool is introduced. RECOApy streamlines the steps of data recording and pre-processing required in end-to-end speech-based applications. The tool implements an easy-to-use interface for prompted speech recording, spectrogram and waveform analysis, utterance-level normalisation and silence trimming, as well grapheme-to-phoneme conversion of the prompts in eight languages: Czech, English, French, German, Italian, Polish, Romanian and Spanish. The grapheme-to-phoneme (G2P) converters are deep neural network (DNN) based architectures trained on lexicons extracted from the Wiktionary online collaborative resource. With the different degree of orthographic transparency, as well as the varying amount of phonetic entries across the languages, the DNN's hyperparameters are optimised with an evolution strategy. The phoneme and word error rates of the resulting G2P converters are presented and discussed. The tool, the processed phonetic lexicons and trained G2P models are made freely available.

Convolutional Neural Networks (CNNs) have been successfully used in various Music Information Retrieval (MIR) tasks, both as end-to-end models and as feature extractors for more complex systems. However, the MIR field is still dominated by the classical VGG-based CNN architecture variants, often in combination with more complex modules such as attention, and/or techniques such as pre-training on large datasets. Deeper models such as ResNet -- which surpassed VGG by a large margin in other domains -- are rarely used in MIR. One of the main reasons for this, as we will show, is the lack of generalization of deeper CNNs in the music domain. In this paper, we present a principled way to make deep architectures like ResNet competitive for music-related tasks, based on well-designed regularization strategies. In particular, we analyze the recently introduced Receptive-Field Regularization and Shake-Shake, and show that they significantly improve the generalization of deep CNNs on music-related tasks, and that the resulting deep CNNs can outperform current more complex models such as CNNs augmented with pre-training and attention. We demonstrate this on two different MIR tasks and two corresponding datasets, thus offering our deep regularized CNNs as a new baseline for these datasets, which can also be used as a feature-extracting module in future, more complex approaches.

This paper presents an adversarial learning method for recognition-synthesis based non-parallel voice conversion. A recognizer is used to transform acoustic features into linguistic representations while a synthesizer recovers output features from the recognizer outputs together with the speaker identity. By separating the speaker characteristics from the linguistic representations, voice conversion can be achieved by replacing the speaker identity with the target one. In our proposed method, a speaker adversarial loss is adopted in order to obtain speaker-independent linguistic representations using the recognizer. Furthermore, discriminators are introduced and a generative adversarial network (GAN) loss is used to prevent the predicted features from being over-smoothed. For training model parameters, a strategy of pre-training on a multi-speaker dataset and then fine-tuning on the source-target speaker pair is designed. Our method achieved higher similarity than the baseline model that obtained the best performance in Voice Conversion Challenge 2018.

In this paper, we propose a domain adaptation framework to address the device mismatch issue in acoustic scene classification leveraging upon neural label embedding (NLE) and relational teacher student learning (RTSL). Taking into account the structural relationships between acoustic scene classes, our proposed framework captures such relationships which are intrinsically device-independent. In the training stage, transferable knowledge is condensed in NLE from the source domain. Next in the adaptation stage, a novel RTSL strategy is adopted to learn adapted target models without using paired source-target data often required in conventional teacher student learning. The proposed framework is evaluated on the DCASE 2018 Task1b data set. Experimental results based on AlexNet-L deep classification models confirm the effectiveness of our proposed approach for mismatch situations. NLE-alone adaptation compares favourably with the conventional device adaptation and teacher student based adaptation techniques. NLE with RTSL further improves the classification accuracy.