Although recent neural text-to-speech (TTS) systems have achieved high-quality speech synthesis, there are cases where a TTS system generates low-quality speech, mainly caused by limited training data or information loss during knowledge distillation. Therefore, we propose a novel method to improve speech quality by training a TTS model under the supervision of perceptual loss, which measures the distance between the maximum possible speech quality score and the predicted one. We first pre-train a mean opinion score (MOS) prediction model and then train a TTS model to maximize the MOS of synthesized speech using the pre-trained MOS prediction model. The proposed method can be applied independently regardless of the TTS model architecture or the cause of speech quality degradation and efficiently without increasing the inference time or model complexity. The evaluation results for the MOS and phone error rate demonstrate that our proposed approach improves previous models in terms of both naturalness and intelligibility.
In recent years, various flow-based generative models have been proposed to generate high-fidelity waveforms in real-time. However, these models require either a well-trained teacher network or a number of flow steps making them memory-inefficient. In this paper, we propose a novel generative model called WaveNODE which exploits a continuous normalizing flow for speech synthesis. Unlike the conventional models, WaveNODE places no constraint on the function used for flow operation, thus allowing the usage of more flexible and complex functions. Moreover, WaveNODE can be optimized to maximize th…
While deep learning has made impressive progress in speech synthesis and voice conversion, the assessment of the synthesized speech is still carried out by human participants. Several recent papers have proposed deep-learning-based assessment models and shown the potential to automate the speech quality assessment. To improve the previously proposed assessment model, MOSNet, we propose three models using cluster-based modeling methods: using a global quality token (GQT) layer, using an Encoding Layer, and using both of them. We perform experiments using the evaluation results of the Voice Conv…
We propose SpeechPainter, a model for filling in gaps of up to one second in speech samples by leveraging an auxiliary textual input. We demonstrate that the model performs speech inpainting with the appropriate content, while maintaining speaker identity, prosody and recording environment conditions, and generalizing to unseen speakers. Our approach significantly outperforms baselines constructed using adaptive TTS, as judged by human raters in side-by-side preference and MOS tests.
In this work, we present the SOMOS dataset, the first large-scale mean opinion scores (MOS) dataset consisting of solely neural text-to-speech (TTS) samples. It can be employed to train automatic MOS prediction systems focused on the assessment of modern synthesizers, and can stimulate advancements in acoustic model evaluation. It consists of 20K synthetic utterances of the LJ Speech voice, a public domain speech dataset which is a common benchmark for building neural acoustic models and vocoders. Utterances are generated from 200 TTS systems including vanilla neural acoustic models as well as…
We aim to characterize how different speakers contribute to the perceived output quality of multi-speaker Text-to-Speech (TTS) synthesis. We automatically rate the quality of TTS using a neural network (NN) trained on human mean opinion score (MOS) ratings. First, we train and evaluate our NN model on 13 different TTS and voice conversion (VC) systems from the ASVSpoof 2019 Logical Access (LA) Dataset. Since it is not known how best to represent speech for this task, we compare 8 different representations alongside MOSNet frame-based features. Our representations include image-based spectrogra…
National University of Ireland Galway（爱尔兰国立大学戈尔韦分校）；University Politehnica of Bucharest（布加勒斯特理工大学）
Speech synthesis has come a long way as current text-to-speech (TTS) models can now generate natural human-sounding speech. However, most of the TTS research focuses on using adult speech data and there has been very limited work done on child speech synthesis. This study developed and validated a training pipeline for fine-tuning state-of-the-art (SOTA) neural TTS models using child speech datasets. This approach adopts a multi-speaker TTS retuning workflow to provide a transfer-learning pipeline. A publicly available child speech dataset was cleaned to provide a smaller subset of approximate…
Nagoya University（名古屋大学）；National Institute of Informatics（国立信息学研究所）
An effective approach to automatically predict the subjective rating for synthetic speech is to train on a listening test dataset with human-annotated scores. Although each speech sample in the dataset is rated by several listeners, most previous works only used the mean score as the training target. In this work, we present LDNet, a unified framework for mean opinion score (MOS) prediction that predicts the listener-wise perceived quality given the input speech and the listener identity. We reflect recent advances in LD modeling, including design choices of the model architecture, and propose…
We have been working on speech synthesis for rakugo (a traditional Japanese form of verbal entertainment similar to one-person stand-up comedy) toward speech synthesis that authentically entertains audiences. In this paper, we propose a novel evaluation methodology using synthesized rakugo speech and real rakugo speech uttered by professional performers of three different ranks. The naturalness of the synthesized speech was comparable to that of the human speech, but the synthesized speech entertained listeners less than the performers of any rank. However, we obtained some interesting insight…
As part of the Human-Computer Interaction field, Expressive speech synthesis is a very rich domain as it requires knowledge in areas such as machine learning, signal processing, sociology, psychology. In this Chapter, we will focus mostly on the technical side. From the recording of expressive speech to its modeling, the reader will have an overview of the main paradigms used in this field, through some of the most prominent systems and methods. We explain how speech can be represented and encoded with audio features. We present a history of the main methods of Text-to-Speech synthesis: concat…
Research & Development Group, Hitachi, Ltd.（日立公司研发集团）
In this paper we propose a new cross-lingual Voice Conversion (VC) approach which can generate all speech parameters (MCEP, LF0, BAP) from one DNN model using PPGs (Phonetic PosteriorGrams) extracted from inputted speech using several ASR acoustic models. Using the proposed VC method, we tried three different approaches to build a multilingual TTS system without recording a multilingual speech corpus. A listening test was carried out to evaluate both speech quality (naturalness) and voice similarity between converted speech and target speech. The results show that Approach 1 achieved the highe…
While deep learning-based text-to-speech (TTS) models such as VITS have shown excellent results, they typically require a sizable set of high-quality <text, audio> pairs to train, which is expensive to collect. So far, most languages in the world still lack the training data needed to develop TTS systems. This paper proposes two improvement methods for the two problems faced by low-resource Mongolian speech synthesis: a) In view of the lack of high-quality <text, audio> pairs of data, it is difficult to model the mapping problem from linguistic features to acoustic features. Improvements are m…
Automatic methods to predict Mean Opinion Score (MOS) of listeners have been researched to assure the quality of Text-to-Speech systems. Many previous studies focus on architectural advances (e.g. MBNet, LDNet, etc.) to capture relations between spectral features and MOS in a more effective way and achieved high accuracy. However, the optimal representation in terms of generalization capability still largely remains unknown. To this end, we compare the performance of Self-Supervised Learning (SSL) features obtained by the wav2vec framework to that of spectral features such as magnitude of spec…
Contrastive Predictive Coding (CPC) is a representation learning method that maximizes the mutual information between intermediate latent representations and the output of a given model. It can be used to effectively initialize the encoder of an Automatic Speech Recognition (ASR) model. We present a novel modification of CPC called Guided Contrastive Predictive Coding (GCPC). Our proposed method maximizes the mutual information between representations from a prior-knowledge model and the output of the model being pre-trained, allowing prior knowledge injection during pre-training. We validate …
Several studies have proposed deep-learning-based models to predict the mean opinion score (MOS) of synthesized speech, showing the possibility of replacing human raters. However, inter- and intra-rater variability in MOSs makes it hard to ensure the high performance of the models. In this paper, we propose a multi-task learning (MTL) method to improve the performance of a MOS prediction model using the following two auxiliary tasks: spoofing detection (SD) and spoofing type classification (STC). Besides, we use the focal loss to maximize the synergy between SD and STC for MOS prediction. Expe…
Brain-computer interface uses brain signals to control external devices without actual control behavior. Recently, speech imagery has been studied for direct communication using language. Speech imagery uses brain signals generated when the user imagines speech. Unlike motor imagery, speech imagery still has unknown characteristics. Additionally, electroencephalography has intricate and non-stationary properties resulting in insufficient decoding performance. In addition, speech imagery is difficult to utilize spatial features. In this study, we designed length-wise training that allows the mo…
Microsoft Corporation（微软公司）；Microsoft Research（微软研究院）
The INTERSPEECH 2020 Deep Noise Suppression Challenge is intended to promote collaborative research in real-time single-channel Speech Enhancement aimed to maximize the subjective (perceptual) quality of the enhanced speech. A typical approach to evaluate the noise suppression methods is to use objective metrics on the test set obtained by splitting the original dataset. Many publications report reasonable performance on the synthetic test set drawn from the same distribution as that of the training set. However, often the model performance degrades significantly on real recordings. Also, most…
This paper presents a novel optimization framework for automatic speech recognition (ASR) with the aim of reducing hallucinations produced by an ASR model. The proposed framework optimizes the ASR model to maximize an expected factual consistency score between ASR hypotheses and ground-truth transcriptions, where the factual consistency score is computed by a separately trained estimator. Experimental results using the AMI meeting corpus and the VoxPopuli corpus show that the ASR model trained with the proposed framework generates ASR hypotheses that have significantly higher consistency score…
In this paper we propose a Deep Neural Network (DNN) based Speech Enhancement (SE) system that is designed to maximize an approximation of the Short-Time Objective Intelligibility (STOI) measure. We formalize an approximate-STOI cost function and derive analytical expressions for the gradients required for DNN training and show that these gradients have desirable properties when used together with gradient based optimization techniques. We show through simulation experiments that the proposed SE system achieves large improvements in estimated speech intelligibility, when tested on matched and …
The acoustic environment can degrade speech quality during communication (e.g., video call, remote presentation, outside voice recording), and its impact is often unknown. Objective metrics for speech quality have proven challenging to develop given the multi-dimensionality of factors that affect speech quality and the difficulty of collecting labeled data. Hypothesizing the impact of acoustics on speech quality, this paper presents MOSRA: a non-intrusive multi-dimensional speech quality metric that can predict room acoustics parameters (SNR, STI, T60, DRR, and C50) alongside the overall mean …
This paper presents a novel zero-shot learning approach towards personalized speech enhancement through the use of a sparsely active ensemble model. Optimizing speech denoising systems towards a particular test-time speaker can improve performance and reduce run-time complexity. However, test-time model adaptation may be challenging if collecting data from the test-time speaker is not possible. To this end, we propose using an ensemble model wherein each specialist module denoises noisy utterances from a distinct partition of training set speakers. The gating module inexpensively estimates tes…
Tokyo Institute of Technology（东京工业大学）；Tencent Cloud Xiaowei（腾讯云小微）
Recent studies have shown that the benefits provided by self-supervised pre-training and self-training (pseudo-labeling) are complementary. Semi-supervised fine-tuning strategies under the pre-training framework, however, remain insufficiently studied. Besides, modern semi-supervised speech recognition algorithms either treat unlabeled data indiscriminately or filter out noisy samples with a confidence threshold. The dissimilarities among different unlabeled data are often ignored. In this paper, we propose Censer, a semi-supervised speech recognition algorithm based on self-supervised pre-tra…
Human judgments obtained through Mean Opinion Scores (MOS) are the most reliable way to assess the quality of speech signals. However, several recent attempts to automatically estimate MOS using deep learning approaches lack robustness and generalization capabilities, limiting their use in real-world applications. In this work, we present a novel framework, NORESQA-MOS, for estimating the MOS of a speech signal. Unlike prior works, our approach uses non-matching references as a form of conditioning to ground the MOS estimation by neural networks. We show that NORESQA-MOS provides better genera…
Speech quality assessment has been a critical component in many voice communication related applications such as telephony and online conferencing. Traditional intrusive speech quality assessment requires the clean reference of the degraded utterance to provide an accurate quality measurement. This requirement limits the usability of these methods in real-world scenarios. On the other hand, non-intrusive subjective measurement is the ``golden standard" in evaluating speech quality as human listeners can intrinsically evaluate the quality of any degraded speech with ease. In this paper, we prop…
This paper proposes an approach to improve Non-Intrusive speech quality assessment(NI-SQA) based on the residuals between impaired speech and enhanced speech. The difficulty in our task is particularly lack of information, for which the corresponding reference speech is absent. We generate an enhanced speech on the impaired speech to compensate for the absence of the reference audio, then pair the information of residuals with the impaired speech. Compared to feeding the impaired speech directly into the model, residuals could bring some extra helpful information from the contrast in enhanceme…
This paper proposes a deep neural network (DNN)-based multi-channel speech enhancement system in which a DNN is trained to maximize the quality of the enhanced time-domain signal. DNN-based multi-channel speech enhancement is often conducted in the time-frequency (T-F) domain because spatial filtering can be efficiently implemented in the T-F domain. In such a case, ordinary objective functions are computed on the estimated T-F mask or spectrogram. However, the estimated spectrogram is often inconsistent, and its amplitude and phase may change when the spectrogram is converted back to the time…
Carnegie Mellon University（卡内基梅隆大学）；The University of Tokyo（东京大学）
While human evaluation is the most reliable metric for evaluating speech generation systems, it is generally costly and time-consuming. Previous studies on automatic speech quality assessment address the problem by predicting human evaluation scores with machine learning models. However, they rely on supervised learning and thus suffer from high annotation costs and domain-shift problems. We propose SpeechLMScore, an unsupervised metric to evaluate generated speech using a speech-language model. SpeechLMScore computes the average log-probability of a speech signal by mapping it into discrete t…
Background noise is a major source of quality impairments in Voice over Internet Protocol (VoIP) and Public Switched Telephone Network (PSTN) calls. Recent work shows the efficacy of deep learning for noise suppression, but the datasets have been relatively small compared to those used in other domains (e.g., ImageNet) and the associated evaluations have been more focused. In order to better facilitate deep learning research in Speech Enhancement, we present a noisy speech dataset (MS-SNSD) that can scale to arbitrary sizes depending on the number of speakers, noise types, and Speech to Noise …
In this paper, we propose a novel auxiliary loss function for target-speaker automatic speech recognition (ASR). Our method automatically extracts and transcribes target speaker's utterances from a monaural mixture of multiple speakers speech given a short sample of the target speaker. The proposed auxiliary loss function attempts to additionally maximize interference speaker ASR accuracy during training. This will regularize the network to achieve a better representation for speaker separation, thus achieving better accuracy on the target-speaker ASR. We evaluated our proposed method using tw…
University of Southern California（南加州大学）；Microsoft Research（微软研究院）
Perceptual speech quality is an important performance metric for teleconferencing applications. The mean opinion score (MOS) is standardized for the perceptual evaluation of speech quality and is obtained by asking listeners to rate the quality of a speech sample. Recently, there has been increasing research interest in developing models for estimating MOS blindly. Here we propose a multi-task framework to include additional labels and data in training to improve the performance of a blind MOS estimation model. Experimental results indicate that the proposed model can be trained to jointly est…
The University of Texas at Dallas（德克萨斯大学达拉斯分校）；Erik Jonsson School of Electrical & Computer Engineering（埃里克·琼森电气与计算机工程学院）
This study introduces a method to design a curriculum for machine-learning to maximize the efficiency during the training process of deep neural networks (DNNs) for speech emotion recognition. Previous studies in other machine-learning problems have shown the benefits of training a classifier following a curriculum where samples are gradually presented in increasing level of difficulty. For speech emotion recognition, the challenge is to establish a natural order of difficulty in the training set to create the curriculum. We address this problem by assuming that ambiguous samples for humans ar…
The T05 System for The VoiceMOS Challenge 2024: Transfer Learning from Deep Image Classifier to Naturalness MOS Prediction of High-Quality Synthetic Speech
Text-to-speech (TTS) synthesis is the process of producing synthesized speech from text or phoneme input. Traditional TTS models contain multiple processing steps and require external aligners, which provide attention alignments of phoneme-to-frame sequences. As the complexity increases and efficiency decreases with every additional step, there is expanding demand in modern synthesis pipelines for end-to-end TTS with efficient internal aligners. In this work, we propose an end-to-end text-to-waveform network with a novel reinforcement learning based duration search method. Our proposed generat…
Perceptual evaluation of speech quality (PESQ) requires a clean speech reference as input, but predicts the results from (reference-free) absolute category rating (ACR) tests. In this work, we train a fully convolutional recurrent neural network (FCRN) as deep noise suppression (DNS) model, with either a non-intrusive or an intrusive PESQNet, where only the latter has access to a clean speech reference. The PESQNet is used as a mediator providing a perceptual loss during the DNS training to maximize the PESQ score of the enhanced speech signal. For the intrusive PESQNet, we investigate two top…
University of Science and Technology of China（中国科学技术大学）；Microsoft Research Asia（微软亚洲研究院）；Microsoft Azure Speech（微软Azure语音）
Mean opinion score (MOS) is a popular subjective metric to assess the quality of synthesized speech, and usually involves multiple human judges to evaluate each speech utterance. To reduce the labor cost in MOS test, multiple methods have been proposed to automatically predict MOS scores. To our knowledge, for a speech utterance, all previous works only used the average of multiple scores from different judges as the training target and discarded the score of each individual judge, which did not well exploit the precious MOS training data. In this paper, we propose MBNet, a MOS predictor with …
Samsung R&D Institute Philippines（三星菲律宾研发研究所）；University of the Philippines（菲律宾大学）
Speech is converted to digital signals using speech coding for efficient transmission. However, this often lowers the quality and bandwidth of speech. This paper explores the application of convolutional neural networks for Artificial Bandwidth Expansion (ABE) and speech enhancement on coded speech, particularly Adaptive Multi-Rate (AMR) used in 2G cellular phone calls. In this paper, we introduce AMRConvNet: a convolutional neural network that performs ABE and speech enhancement on speech encoded with AMR. The model operates directly on the time-domain for both input and output speech but opt…
Although automatic speech recognition (ASR) task has gained remarkable success by sequence-to-sequence models, there are two main mismatches between its training and testing that might lead to performance degradation: 1) The typically used cross-entropy criterion aims to maximize log-likelihood of the training data, while the performance is evaluated by word error rate (WER), not log-likelihood; 2) The teacher-forcing method leads to the dependence on ground truth during training, which means that model has never been exposed to its own prediction before testing. In this paper, we propose an o…
Speech quality in online conferencing applications is typically assessed through human judgements in the form of the mean opinion score (MOS) metric. Since such a labor-intensive approach is not feasible for large-scale speech quality assessments in most settings, the focus has shifted towards automated MOS prediction through end-to-end training of deep neural networks (DNN). Instead of training a network from scratch, we propose to leverage the speech representations from the pre-trained wav2vec-based XLS-R model. However, the number of parameters of such a model exceeds task-specific DNNs by…
