This paper leverages the graph-to-sequence method in neural text-to-speech (GraphTTS), which maps the graph embedding of the input sequence to spectrograms. The graphical inputs consist of node and edge representations constructed from input texts. The encoding of these graphical inputs incorporates syntax information by a GNN encoder module. Besides, applying the encoder of GraphTTS as a graph auxiliary encoder (GAE) can analyse prosody information from the semantic structure of texts. This can remove the manual selection of reference audios process and makes prosody modelling an end-to-end procedure. Experimental analysis shows that GraphTTS outperforms the state-of-the-art sequence-to-sequence models by 0.24 in Mean Opinion Score (MOS). GAE can adjust the pause, ventilation and tones of synthesised audios automatically. This experimental conclusion may give some inspiration to researchers working on improving speech synthesis prosody.
Previous works on expressive speech synthesis mainly focus on current sentence. The context in adjacent sentences is neglected, resulting in inflexible speaking style for the same text, which lacks speech variations. In this paper, we propose a hierarchical framework to model speaking style from context. A hierarchical context encoder is proposed to explore a wider range of contextual information considering structural relationship in context, including inter-phrase and inter-sentence relations. Moreover, to encourage this encoder to learn style representation better, we introduce a novel trai…
Previous works on expressive speech synthesis focus on modelling the mono-scale style embedding from the current sentence or context, but the multi-scale nature of speaking style in human speech is neglected. In this paper, we propose a multi-scale speaking style modelling method to capture and predict multi-scale speaking style for improving the naturalness and expressiveness of synthetic speech. A multi-scale extractor is proposed to extract speaking style embeddings at three different levels from the ground-truth speech, and explicitly guide the training of a multi-scale style predictor bas…
University of Science and Technology of China（中国科学技术大学）
This paper proposes a forward attention method for the sequenceto- sequence acoustic modeling of speech synthesis. This method is motivated by the nature of the monotonic alignment from phone sequences to acoustic sequences. Only the alignment paths that satisfy the monotonic condition are taken into consideration at each decoder timestep. The modified attention probabilities at each timestep are computed recursively using a forward algorithm. A transition agent for forward attention is further proposed, which helps the attention mechanism to make decisions whether to move forward or stay at e…
Duration modelling has become an important research problem once more with the rise of non-attention neural text-to-speech systems. The current approaches largely fall back to relying on previous statistical parametric speech synthesis technology for duration prediction, which poorly models the expressiveness and variability in speech. In this paper, we propose two alternate approaches to improve duration modelling. First, we propose a duration model conditioned on phrasing that improves the predicted durations and provides better modelling of pauses. We show that the duration model conditione…
We propose a novel Multi-Scale Spectrogram (MSS) modelling approach to synthesise speech with an improved coarse and fine-grained prosody. We present a generic multi-scale spectrogram prediction mechanism where the system first predicts coarser scale mel-spectrograms that capture the suprasegmental information in speech, and later uses these coarser scale mel-spectrograms to predict finer scale mel-spectrograms capturing fine-grained prosody. We present details for two specific versions of MSS called Word-level MSS and Sentence-level MSS where the scales in our system are motivated by the ling…
VoxInstruct: Expressive Human Instruction-to-Speech Generation with Unified Multilingual Codec Language Modelling
Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）；BNRist, Tsinghua University（清华大学BNRist）；Key Laboratory of Pervasive Computing, Ministry of Education（教育部普适计算重点实验室）
Despite prosody is related to the linguistic information up to the discourse structure, most text-to-speech (TTS) systems only take into account that within each sentence, which makes it challenging when converting a paragraph of texts into natural and expressive speech. In this paper, we propose to use the text embeddings of the neighboring sentences to improve the prosody generation for each utterance of a paragraph in an end-to-end fashion without using any explicit prosody features. More specifically, cross-utterance (CU) context vectors, which are produced by an additional CU encoder base…
Unlike human speakers, typical text-to-speech (TTS) systems are unable to produce multiple distinct renditions of a given sentence. This has previously been addressed by adding explicit external control. In contrast, generative models are able to capture a distribution over multiple renditions and thus produce varied renditions using sampling. Typical neural TTS models learn the average of the data because they minimise mean squared error. In the context of prosody, taking the average produces flatter, more boring speech: an "average prosody". A generative model that can synthesise multiple pr…
We propose two novel techniques --- stacking bottleneck features and minimum generation error training criterion --- to improve the performance of deep neural network (DNN)-based speech synthesis. The techniques address the related issues of frame-by-frame independence and ignorance of the relationship between static and dynamic features, within current typical DNN-based synthesis frameworks. Stacking bottleneck features, which are an acoustically--informed linguistic representation, provides an efficient way to include more detailed linguistic context at the input. The minimum generation erro…
Stellenbosch University（斯泰伦博斯大学）；The University of Edinburgh（爱丁堡大学）
For our submission to the ZeroSpeech 2019 challenge, we apply discrete latent-variable neural networks to unlabelled speech and use the discovered units for speech synthesis. Unsupervised discrete subword modelling could be useful for studies of phonetic category learning in infants or in low-resource speech technology requiring symbolic input. We use an autoencoder (AE) architecture with intermediate discretisation. We decouple acoustic unit discovery from speaker modelling by conditioning the AE's decoder on the training speaker identity. At test time, unit discovery is performed on speech f…
Whilst recent neural text-to-speech (TTS) approaches produce high-quality speech, they typically require a large amount of recordings from the target speaker. In previous work, a 3-step method was proposed to generate high-quality TTS while greatly reducing the amount of data required for training. However, we have observed a ceiling effect in the level of naturalness achievable for highly expressive voices when using this approach. In this paper, we present a method for building highly expressive TTS voices with as little as 15 minutes of speech data from the target speaker. Compared to the c…
Human-Computer Communications Laboratory（人机通信实验室）；The Chinese University of Hong Kong（香港中文大学）；SpeechX Limited（SpeechX有限公司）；University of Cambridge（剑桥大学）
Though significant progress has been made for the voice conversion (VC) of typical speech, VC for atypical speech, e.g., dysarthric and second-language (L2) speech, remains a challenge, since it involves correcting for atypical prosody while maintaining speaker identity. To address this issue, we propose a VC system with explicit prosodic modelling and deep speaker embedding (DSE) learning. First, a speech-encoder strives to extract robust phoneme embeddings from atypical speech. Second, a prosody corrector takes in phoneme embeddings to infer typical phoneme duration and pitch values. Third, …
Generative adversarial networks have seen rapid development in recent years and have led to remarkable improvements in generative modelling of images. However, their application in the audio domain has received limited attention, and autoregressive models, such as WaveNet, remain the state of the art in generative modelling of audio signals such as human speech. To address this paucity, we introduce GAN-TTS, a Generative Adversarial Network for Text-to-Speech. Our architecture is composed of a conditional feed-forward generator producing raw speech audio, and an ensemble of discriminators whic…
ShanghaiTech University（上海科技大学）；Cambridge University（剑桥大学）；Neurowave Ai Limited（Neurowave人工智能有限公司）；Shanghai Jiao Tong University（上海交通大学）；University College London（伦敦大学学院）
Modelling prosody variation is critical for synthesizing natural and expressive speech in end-to-end text-to-speech (TTS) systems. In this paper, a cross-utterance conditional VAE (CUC-VAE) is proposed to estimate a posterior probability distribution of the latent prosody features for each phoneme by conditioning on acoustic features, speaker information, and text features obtained from both past and future sentences. At inference time, instead of the standard Gaussian distribution used by VAE, CUC-VAE allows sampling from an utterance-specific prior distribution conditioned on cross-utterance…
Ping An Technology (Shenzhen) Co., Ltd.（平安科技（深圳）有限公司）
This paper introduces a graphical representation approach of prosody boundary (GraphPB) in the task of Chinese speech synthesis, intending to parse the semantic and syntactic relationship of input sequences in a graphical domain for improving the prosody performance. The nodes of the graph embedding are formed by prosodic words, and the edges are formed by the other prosodic boundaries, namely prosodic phrase boundary (PPH) and intonation phrase boundary (IPH). Different Graph Neural Networks (GNN) like Gated Graph Neural Network (GGNN) and Graph Long Short-term Memory (G-LSTM) are utilised as…
Institute of Behavioural Sciences, University of Helsinki（赫尔辛基大学行为科学研究所）；Aalto University（阿尔托大学）；University of Alberta（阿尔伯塔大学）；Institute for Reconstructive Sciences in Medicine (iRSM), Misericordia Hospital（misericordia 医院医学重建科学研究所（iRSM））
Prominences and boundaries are the essential constituents of prosodic structure in speech. They provide for means to chunk the speech stream into linguistically relevant units by providing them with relative saliences and demarcating them within coherent utterance structures. Prominences and boundaries have both been widely used in both basic research on prosody as well as in text-to-speech synthesis. However, there are no representation schemes that would provide for both estimating and modelling them in a unified fashion. Here we present an unsupervised unified account for estimating and rep…
A Spoken dialogue system for an unseen language is referred to as Zero resource speech. It is especially beneficial for developing applications for languages that have low digital resources. Zero resource speech synthesis is the task of building text-to-speech (TTS) models in the absence of transcriptions. In this work, speech is modelled as a sequence of transient and steady-state acoustic units, and a unique set of acoustic units is discovered by iterative training. Using the acoustic unit sequence, TTS models are trained. The main goal of this work is to improve the synthesis quality of zer…
Classical parametric speech coding techniques provide a compact representation for speech signals. This affords a very low transmission rate but with a reduced perceptual quality of the reconstructed signals. Recently, autoregressive deep generative models such as WaveNet and SampleRNN have been used as speech vocoders to scale up the perceptual quality of the reconstructed signals without increasing the coding rate. However, such models suffer from a very slow signal generation mechanism due to their sample-by-sample modelling approach. In this work, we introduce a new methodology for neural …
Idiap Research Institute（伊迪亚普研究所）；Constantine the Philosopher University in Nitra（尼特拉康斯坦丁哲学家大学）；Institute of Informatics, Slovak Academy of Sciences（斯洛伐克科学院信息学研究所）
Using phonological speech vocoding, we propose a platform for exploring relations between phonology and speech processing, and in broader terms, for exploring relations between the abstract and physical structures of a speech signal. Our goal is to make a step towards bridging phonology and speech processing and to contribute to the program of Laboratory Phonology. We show three application examples for laboratory phonology: compositional phonological speech modelling, a comparison of phonological systems and an experimental phonological parametric text-to-speech (TTS) system. The featural rep…
National Institute of Informatics（国立信息学研究所）；KTH Royal Institute of Technology（KTH皇家理工学院）；University of Edinburgh（爱丁堡大学）
Generating versatile and appropriate synthetic speech requires control over the output expression separate from the spoken text. Important non-textual speech variation is seldom annotated, in which case output control must be learned in an unsupervised fashion. In this paper, we perform an in-depth study of methods for unsupervised learning of control in statistical speech synthesis. For example, we show that popular unsupervised training heuristics can be interpreted as variational inference in certain autoencoder models. We additionally connect these models to VQ-VAEs, another, recently-prop…
Tilburg University（蒂尔堡大学）；Laboratoire de Sciences Cognitives et Psycholinguistique, ENS（巴黎高等师范学院认知科学与心理语言学实验室）；Tampere University（坦佩雷大学）；Aalto University（阿尔托大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）
We present the visually-grounded language modelling track that was introduced in the Zero-Resource Speech challenge, 2021 edition, 2nd round. We motivate the new track and discuss participation rules in detail. We also present the two baseline systems that were developed for this track.
Language models (LMs) for text data have been studied extensively for their usefulness in language generation and other downstream tasks. However, language modelling purely in the speech domain is still a relatively unexplored topic, with traditional speech LMs often depending on auxiliary text LMs for learning distributional aspects of the language. For the English language, these LMs treat words as atomic units, which presents inherent challenges to language modelling in the speech domain. In this paper, we propose a novel LSTM-based generative speech LM that is inspired by the CBOW model an…
Sir C.V. Raman Centre for Physics and Music, Jadavpur University（贾达普大学C.V.拉曼物理与音乐中心）；Department of Humanities and Social Sciences, IIT Kharagpur（印度理工学院卡哈拉格普尔分校人文与社会科学系）；Shrutinandan School of Music, Kolkata（加尔各答Shrutinandan音乐学院）；Department of Physics, Jadavpur University（贾达普大学物理系）；Department of Electrical Engineering, Jadavpur University（贾达普大学电气工程系）；School of Languages and Linguistics, Jadavpur University（贾达普大学语言与语言学学院）
At present emotion extraction from speech is a very important issue due to its diverse applications. Hence, it becomes absolutely necessary to obtain models that take into consideration the speaking styles of a person, vocal tract information, timbral qualities and other congenital information regarding his voice. Our speech production system is a nonlinear system like most other real world systems. Hence the need arises for modelling our speech information using nonlinear techniques. In this work we have modelled our articulation system using nonlinear multifractal analysis. The multifractal …
Data61, CSIRO（澳大利亚联邦科学与工业研究组织数据61所）；University of New South Wales（新南威尔士大学）
Speech emotion recognition is a challenging task and heavily depends on hand-engineered acoustic features, which are typically crafted to echo human perception of speech signals. However, a filter bank that is designed from perceptual evidence is not always guaranteed to be the best in a statistical modelling framework where the end goal is for example emotion classification. This has fuelled the emerging trend of learning representations from raw speech especially using deep learning neural networks. In particular, a combination of Convolution Neural Networks (CNNs) and Long Short Term Memory…
University of Oxford（牛津大学）；The Alan Turing Institute（艾伦·图灵研究所）；University of Sheffield（谢菲尔德大学）；Queen Mary University of London（伦敦玛丽女王大学）
Bipolar disorder (BD) and borderline personality disorder (BPD) are two chronic mental health conditions that clinicians find challenging to distinguish based on clinical interviews, due to their overlapping symptoms. In this work, we investigate the automatic detection of these two conditions by modelling both verbal and non-verbal cues in a set of interviews. We propose a new approach of modelling short-term features with visibility-signature transform, and compare it with widely used high-level statistical functions. We demonstrate the superior performance of our proposed signature-based mo…
IIT Bombay（孟买印度理工学院）；University of Cambridge（剑桥大学）；IIT Kharagpur（卡哈拉格普尔印度理工学院）
Automatic speech recognition (ASR) in Sanskrit is interesting, owing to the various linguistic peculiarities present in the language. The Sanskrit language is lexically productive, undergoes euphonic assimilation of phones at the word boundaries and exhibits variations in spelling conventions and in pronunciations. In this work, we propose the first large scale study of automatic speech recognition (ASR) in Sanskrit, with an emphasis on the impact of unit selection in Sanskrit ASR. In this work, we release a 78 hour ASR dataset for Sanskrit, which faithfully captures several of the linguistic …
The performances of automatic speech recognition (ASR) systems degrade drastically under noisy conditions. Explicit distortion modelling (EDM), as a feature compensation step, is able to enhance ASR systems under such conditions by simulating the in-domain noisy speeches from the clean counterparts. Yet, existing distortion models are either non-trainable or unexplainable and often lack controllability and generalization ability. In this paper, we propose a fully explainable and controllable model: DENT-DDSP to achieve EDM. DENT-DDSP utilizes novel differentiable digital signal processing (DDS…
ParsVoice: A Large-Scale Multi-Speaker Persian Speech Corpus for Text-to-Speech Synthesis
School of Electrical and Computer Engineering, University of Tehran（塔里哈大学电气与计算机工程学院）；Institute for Research in Fundamental Sciences (IPM)（基础科学研究所（IPM））
Investigation of Deep Neural Network Acoustic Modelling Approaches for Low Resource Accented Mandarin Speech Recognition
Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院人机智能协同系统重点实验室）；Cambridge University Engineering Dept（剑桥大学工程系）；The Chinese University of Hong Kong（香港中文大学）
针对低资源多口音普通话识别，本文比较多种DNN声学建模方案，并提出显式利用口音信息的改进MLAN tandem HMM系统，使字错误率相对基线绝对降低0.8%至1.5%。
Queensland University of Technology（昆士兰科技大学）；SRI International（SRI国际研究所）
This paper presents a novel framework for Speech Activity Detection (SAD). Inspired by the recent success of multi-task learning approaches in the speech processing domain, we propose a novel joint learning framework for SAD. We utilise generative adversarial networks to automatically learn a loss function for joint prediction of the frame-wise speech/ non-speech classifications together with the next audio segment. In order to exploit the temporal relationships within the input signal, we propose a temporal discriminator which aims to ensure that the predicted signal is temporally consistent.…
Paul Sabatier University（保罗萨巴蒂尔大学）；CNRS（法国国家科学研究中心）；Lalilo（拉利洛公司）
Automatic recognition systems for child speech are lagging behind those dedicated to adult speech in the race of performance. This phenomenon is due to the high acoustic and linguistic variability present in child speech caused by their body development, as well as the lack of available child speech data. Young readers speech additionally displays peculiarities, such as slow reading rate and presence of reading mistakes, that hardens the task. This work attempts to tackle the main challenges in phone acoustic modelling for young child speech with limited data, and improve understanding of stre…
Perceptually-inspired objective functions such as the perceptual evaluation of speech quality (PESQ), signal-to-distortion ratio (SDR), and short-time objective intelligibility (STOI), have recently been used to optimize performance of deep-learning-based speech enhancement algorithms. These objective functions, however, do not always strongly correlate with a listener's assessment of perceptual quality, so optimizing with these measures often results in poorer performance in real-world scenarios. In this work, we propose an attention-based enhancement approach that uses learned speech embeddi…
End-to-End automatic speech recognition (ASR) models aim to learn a generalised speech representation to perform recognition. In this domain there is little research to analyse internal representation dependencies and their relationship to modelling approaches. This paper investigates cross-domain language model dependencies within transformer architectures using SVCCA and uses these insights to exploit modelling approaches. It was found that specific neural representations within the transformer layers exhibit correlated behaviour which impacts recognition performance. Altogether, this work p…
A new label smoothing method that makes use of prior knowledge of a language at human level, homophone, is proposed in this paper for automatic speech recognition (ASR). Compared with its forerunners, the proposed method uses pronunciation knowledge of homophones in a more complex way. End-to-end ASR models that learn acoustic model and language model jointly and modelling units of characters are necessary conditions for this method. Experiments with hybrid CTC sequence-to-sequence model show that the new method can reduce character error rate (CER) by 0.4% absolutely.
In this paper, a time delay neural network (TDNN) based acoustic model is proposed to implement a fast-converged acoustic modeling for Korean speech recognition. The TDNN has an advantage in fast-convergence where the amount of training data is limited, due to subsampling which excludes duplicated weights. The TDNN showed an absolute improvement of 2.12% in terms of character error rate compared to feed forward neural network (FFNN) based modelling for Korean speech corpora. The proposed model converged 1.67 times faster than a FFNN-based model did.
Stellenbosch University（斯泰伦博斯大学）；National University of Singapore（新加坡国立大学）
This paper considers the impact of automatic segmentation on the fully-automatic, semi-supervised training of automatic speech recognition (ASR) systems for five-lingual code-switched (CS) speech. Four automatic segmentation techniques were evaluated in terms of the recognition performance of an ASR system trained on the resulting segments in a semi-supervised manner. The system's output was compared with the recognition rates achieved by a semi-supervised system trained on manually assigned segments. Three of the automatic techniques use a newly proposed convolutional neural network (CNN) mod…
