We introduce SPEAR-TTS, a multi-speaker text-to-speech (TTS) system that can be trained with minimal supervision. By combining two types of discrete speech representations, we cast TTS as a composition of two sequence-to-sequence tasks: from text to high-level semantic tokens (akin to "reading") and from semantic tokens to low-level acoustic tokens ("speaking"). Decoupling these two tasks enables training of the "speaking" module using abundant audio-only data, and unlocks the highly efficient combination of pretraining and backtranslation to reduce the need for parallel data when training the "reading" component. To control the speaker identity, we adopt example prompting, which allows SPEAR-TTS to generalize to unseen speakers using only a short sample of 3 seconds, without any explicit speaker representation or speaker-id labels. Our experiments demonstrate that SPEAR-TTS achieves a character error rate that is competitive with state-of-the-art methods using only 15 minutes of parallel data, while matching ground-truth speech in terms of naturalness and acoustic quality, as measured in subjective tests.
In this paper, we construct a Japanese audiobook speech corpus called "J-MAC" for speech synthesis research. With the success of reading-style speech synthesis, the research target is shifting to tasks that use complicated contexts. Audiobook speech synthesis is a good example that requires cross-sentence, expressiveness, etc. Unlike reading-style speech, speaker-specific expressiveness in audiobook speech also becomes the context. To enhance this research, we propose a method of constructing a corpus from audiobooks read by professional speakers. From many audiobooks and their texts, our meth…
Recently, more and more zero-shot voice conversion algorithms have been proposed. As a fundamental part of zero-shot voice conversion, speaker embeddings are the key to improving the converted speech's speaker similarity. In this paper, we study the impact of speaker embeddings on zero-shot voice conversion performance. To better represent the characteristics of the target speaker and improve the speaker similarity in zero-shot voice conversion, we propose a novel speaker representation method in this paper. Our method combines the advantages of D-vector, global style token (GST) based speaker…
In recent years, emotional text-to-speech has shown considerable progress. However, it requires a large amount of labeled data, which is not easily accessible. Even if it is possible to acquire an emotional speech dataset, there is still a limitation in controlling emotion intensity. In this work, we propose a novel method for cross-speaker emotion transfer and manipulation using vector arithmetic in latent style space. By leveraging only a few labeled samples, we generate emotional speech from reading-style speech without losing the speaker identity. Furthermore, emotion strength is readily c…
From Reliable Text to Real Voices: Trust-Aware Progressive Adaptation for Low-Resource TTS
Beijing Logic Intelligence Technology（北京逻辑智能科技有限公司）；University of Washington（华盛顿大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；University of California, USA（加州大学）；Northwestern University, USA（西北大学）
Duke Kunshan University（昆山杜克大学）；Duke University（杜克大学）
This report describes the submission of the DKU-DukeECE team to the self-supervision speaker verification task of the 2021 VoxCeleb Speaker Recognition Challenge (VoxSRC). Our method employs an iterative labeling framework to learn self-supervised speaker representation based on a deep neural network (DNN). The framework starts with training a self-supervision speaker embedding network by maximizing agreement between different segments within an utterance via a contrastive loss. Taking advantage of DNN's ability to learn from data with label noise, we propose to cluster the speaker embedding o…
Adaptive text to speech (TTS) can synthesize new voices in zero-shot scenarios efficiently, by using a well-trained source TTS model without adapting it on the speech data of new speakers. Considering seen and unseen speakers have diverse characteristics, zero-shot adaptive TTS requires strong generalization ability on speaker characteristics, which brings modeling challenges. In this paper, we develop AdaSpeech 4, a zero-shot adaptive TTS system for high-quality speech synthesis. We model the speaker characteristics systematically to improve the generalization on new speakers. Generally, the …
Speaking Clearly: A Simplified Whisper-Based Codec for Low-Bitrate Speech Coding
School of Computer Science and Artificial Intelligence（计算机科学与人工智能学院）；Wuhan University of Technology（武汉理工大学）；NEC Corporation（日本电气株式会社）；The Hong Kong Polytechnic University（香港理工大学）
Cross-speaker style transfer (CSST) in text-to-speech (TTS) synthesis aims at transferring a speaking style to the synthesised speech in a target speaker's voice. Most previous CSST approaches rely on expensive high-quality data carrying desired speaking style during training and require a reference utterance to obtain speaking style descriptors as conditioning on the generation of a new sentence. This work presents Referee, a robust reference-free CSST approach for expressive TTS, which fully leverages low-quality data to learn speaking styles from text. Referee is built by cascading a text-t…
While recent neural text-to-speech (TTS) systems perform remarkably well, they typically require a substantial amount of recordings from the target speaker reading in the desired speaking style. In this work, we present a novel 3-step methodology to circumvent the costly operation of recording large amounts of target data in order to build expressive style voices with as little as 15 minutes of such recordings. First, we augment data via voice conversion by leveraging recordings in the desired speaking style from other speakers. Next, we use that synthetic data on top of the available recordin…
Unsupervised representation learning has shown remarkable achievement by reducing the performance gap with supervised feature learning, especially in the image domain. In this study, to extend the technique of unsupervised learning to the speech domain, we propose the Momentum Contrast for VoxCeleb (MoCoVox) as a form of learning mechanism. We pre-trained the MoCoVox on the VoxCeleb1 by implementing instance discrimination. Applying MoCoVox for speaker verification revealed that it outperforms the state-of-the-art metric learning-based approach by a large margin. We also empirically demonstrat…
U3-xi: Pushing the Boundaries of Speaker Recognition by Incorporating Uncertainty
Department of Electrical and Eletronic Engineering, Faculty of Engineering, and Research Centre for Data Science and Artificial Intelligence (RC-DSAI), The Hong Kong Polytechnic University（电子与电气工程系，工程学院，数据科学与人工智能研究中心（RC-DSAI），香港理工大学）
The scarcity of training data and the large speaker variation in dysarthric speech lead to poor accuracy and poor speaker generalization of spoken language understanding systems for dysarthric speech. Through work on the speech features, we focus on improving the model generalization ability with limited dysarthric data. Factorized Hierarchical Variational Auto-Encoders (FHVAE) trained unsupervisedly have shown their advantage in disentangling content and speaker representations. Earlier work showed that the dysarthria shows in both feature vectors. Here, we add adversarial training to bridge …
Self-supervised learning (SSL) methods which learn representations of data without explicit supervision have gained popularity in speech-processing tasks, particularly for single-talker applications. However, these models often have degraded performance for multi-talker scenarios -- possibly due to the domain mismatch -- which severely limits their use for such applications. In this paper, we investigate the adaptation of upstream SSL models to the multi-talker automatic speech recognition (ASR) task under two conditions. First, when segmented utterances are given, we show that adding a target…
Koopman Regularized Deep Speech Disentanglement for Speaker Verification
School of Electronics and Computer Science, University of Southampton（电子与计算机科学学院，南安普顿大学）；Marine Geosciences, National Oceanography Centre（海洋科学，国家海洋学中心）
The Chinese University of Hong Kong（香港中文大学）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）
A key challenge for automatic speech recognition (ASR) systems is to model the speaker level variability. In this paper, compact speaker dependent learning hidden unit contributions (LHUC) are used to facilitate both speaker adaptive training (SAT) and test time unsupervised speaker adaptation for state-of-the-art Conformer based end-to-end ASR systems. The sensitivity during adaptation to supervision error rate is reduced using confidence score based selection of the more "trustworthy" subset of speaker specific data. A confidence estimation module is used to smooth the over-confident Conform…
The objective of this paper is to combine multiple frame-level features into a single utterance-level representation considering pairwise relationship. For this purpose, we propose a novel graph attentive feature aggregation module by interpreting each frame-level feature as a node of a graph. The inter-relationship between all possible pairs of features, typically exploited indirectly, can be directly modeled using a graph. The module comprises a graph attention layer and a graph pooling layer followed by a readout operation. The graph attention layer first models the non-Euclidean data manif…
Graph-based temporal classification (GTC), a generalized form of the connectionist temporal classification loss, was recently proposed to improve automatic speech recognition (ASR) systems using graph-based supervision. For example, GTC was first used to encode an N-best list of pseudo-label sequences into a graph for semi-supervised learning. In this paper, we propose an extension of GTC to model the posteriors of both labels and label transitions by a neural network, which can be applied to a wider range of tasks. As an example application, we use the extended GTC (GTC-e) for the multi-speak…
Chinese University of Hong Kong（香港中文大学）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）
Speaker adaptation techniques provide a powerful solution to customise automatic speech recognition (ASR) systems for individual users. Practical application of unsupervised model-based speaker adaptation techniques to data intensive end-to-end ASR systems is hindered by the scarcity of speaker-level data and performance sensitivity to transcription errors. To address these issues, a set of compact and data efficient speaker-dependent (SD) parameter representations are used to facilitate both speaker adaptive training and test-time unsupervised speaker adaptation of state-of-the-art Conformer …
Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；The Chinese University of Hong Kong（香港中文大学）
Modeling the speaker variability is a key challenge for automatic speech recognition (ASR) systems. In this paper, the learning hidden unit contributions (LHUC) based adaptation techniques with compact speaker dependent (SD) parameters are used to facilitate both speaker adaptive training (SAT) and unsupervised test-time speaker adaptation for end-to-end (E2E) lattice-free MMI (LF-MMI) models. An unsupervised model-based adaptation framework is proposed to estimate the SD parameters in E2E paradigm using LF-MMI and cross entropy (CE) criterions. Various regularization methods of the standard L…
LibriConvo: Simulating Conversations from Read Literature for ASR and Diarization
Department of Telecommunications and Artificial Intelligence, Budapest University of Technology and Economics（电信与人工智能系，布达佩斯技术与经济大学）；Speechtex Ltd.（Speechtex公司）；ELTE Research Centre for Linguistics（ELTE语言研究所）
SpeakerCard-1M: An Evidence-Grounded Corpus for In-the-Wild Speaker Verification
Brno University of Technology, Czechia（布拉格技术大学，捷克）；Peking University, China（北京大学，中国）；Xiaomi, China（小米，中国）；Athens University of Economics and Business, Greece（雅典经济与商业大学，希腊）；The Hong Kong Polytechnic University, Hong Kong（香港理工大学，香港）；Nanjing University, China（南京大学，中国）
University of Science and Technology of China（中国科学技术大学）；iFlytek Research（科大讯飞研究院）；Georgia Institute of Technology（佐治亚理工学院）
We propose a separation guided speaker diarization (SGSD) approach by fully utilizing a complementarity of speech separation and speaker clustering. Since the conventional clustering-based speaker diarization (CSD) approach cannot well handle overlapping speech segments, we investigate, in this study, separation-based speaker diarization (SSD) which inherently has the potential to handle the speaker overlap regions. Our preliminary analysis shows that the state-of-the-art Conv-TasNet based speech separation, which works quite well on the simulation data, is unstable in realistic conversational…
Advances in self-supervised learning have significantly reduced the amount of transcribed audio required for training. However, the majority of work in this area is focused on read speech. We explore limited supervision in the domain of conversational speech. While we assume the amount of in-domain data is limited, we augment the model with open source read speech data. The XLS-R model has been shown to perform well with limited adaptation data and serves as a strong baseline. We use untranscribed data for self-supervised learning and semi-supervised training in an autoregressive encoder-decod…
An Exploration of ECAPA-TDNN and x-vector Speaker Representations in Zero-shot Multi-speaker TTS
NTIS Research Centre（NTIS研究中心）；Department of Cybernetics, Faculty of Applied Sciences, University of West Bohemia in Pilsen, Czechia（应用科学学院控制系，西波西米亚大学在比斯伦分校，捷克）
Johns Hopkins University（约翰斯·霍普金斯大学）；Tencent AI Lab（腾讯人工智能实验室）
This paper proposes a new paradigm for handling far-field multi-speaker data in an end-to-end neural network manner, called directional automatic speech recognition (D-ASR), which explicitly models source speaker locations. In D-ASR, the azimuth angle of the sources with respect to the microphone array is defined as a latent variable. This angle controls the quality of separation, which in turn determines the ASR performance. All three functionalities of D-ASR: localization, separation, and recognition are connected as a single differentiable neural network and trained solely based on ASR erro…
Imperial College London（伦敦帝国理工学院）；Facebook London（脸书伦敦）；University of Augsburg（奥格斯堡大学）
The large amount of audiovisual content being shared online today has drawn substantial attention to the prospect of audiovisual self-supervised learning. Recent works have focused on each of these modalities separately, while others have attempted to model both simultaneously in a cross-modal fashion. However, comparatively little attention has been given to leveraging one modality as a training objective to learn from the other. In this work, we propose Learning visual speech Representations from Audio via self-supervision (LiRA). Specifically, we train a ResNet+Conformer model to predict ac…
Do Speech Representations Preserve Regional Accent Across Read and Spontaneous Speech?
Friedrich-Alexander-Universität Erlangen-Nürnberg（弗里德里希-亚历山大-埃尔朗根-纽伦堡大学）；Leibniz Institute for Educational Trajectories (LIfBi)（莱布尼茨教育轨迹研究所）；Otto-Friedrich-Universität Bamberg（奥托-弗里德里希-班贝格大学）
