arXiv subjects

Hiroshi Saruwatari

Publications and source records attributed to Hiroshi Saruwatari.

At least 73 records · Page 4Linked to original sources

arXiv2023

How Generative Spoken Language Modeling Encodes Noisy Speech: Investigation from Phonetics to Syntactics

We examine the speech modeling potential of generative spoken language modeling (GSLM), which involves using learned symbols derived from data rather than phonemes for speech analysis and synthesis. Since GSLM facilitates textless spoken language processing, exploring its effectiveness is critical for paving the way for novel paradigms in spoken-language processing. This paper presents the findings of GSLM's encoding and decoding effectiveness at the spoken-language and speech levels. Through speech resynthesis experiments, we revealed that resynthesis errors occur at the levels ranging from phonology to syntactics and GSLM frequently resynthesizes natural but content-altered speech.

cs.CL↗

arXiv2023

Learning to Speak from Text: Zero-Shot Multilingual Text-to-Speech with Unsupervised Text Pretraining

While neural text-to-speech (TTS) has achieved human-like natural synthetic speech, multilingual TTS systems are limited to resource-rich languages due to the need for paired text and studio-quality audio data. This paper proposes a method for zero-shot multilingual TTS using text-only data for the target language. The use of text-only data allows the development of TTS systems for low-resource languages for which only textual resources are available, making TTS accessible to thousands of languages. Inspired by the strong cross-lingual transferability of multilingual language models, our framework first performs masked language model pretraining with multilingual text-only data. Then we train this model with a paired data in a supervised manner, while freezing a language-aware embedding layer. This allows inference even for languages not included in the paired data but present in the text-only data. Evaluation results demonstrate highly intelligible zero-shot TTS with a character error rate of less than 12% for an unseen language.

eess.AS↗

arXiv2023

Laughter Synthesis using Pseudo Phonetic Tokens with a Large-scale In-the-wild Laughter Corpus

We present a large-scale in-the-wild Japanese laughter corpus and a laughter synthesis method. Previous work on laughter synthesis lacks not only data but also proper ways to represent laughter. To solve these problems, we first propose an in-the-wild corpus comprising $3.5$ hours of laughter, which is to our best knowledge the largest laughter corpus designed for laughter synthesis. We then propose pseudo phonetic tokens (PPTs) to represent laughter by a sequence of discrete tokens, which are obtained by training a clustering model on features extracted from laughter by a pretrained self-supervised model. Laughter can then be synthesized by feeding PPTs into a text-to-speech system. We further show PPTs can be used to train a language model for unconditional laughter generation. Results of comprehensive subjective and objective evaluations demonstrate that the proposed method significantly outperforms a baseline method, and can generate natural laughter unconditionally.

cs.SD↗

arXiv2023

CALLS: Japanese Empathetic Dialogue Speech Corpus of Complaint Handling and Attentive Listening in Customer Center

We present CALLS, a Japanese speech corpus that considers phone calls in a customer center as a new domain of empathetic spoken dialogue. The existing STUDIES corpus covers only empathetic dialogue between a teacher and student in a school. To extend the application range of empathetic dialogue speech synthesis (EDSS), we designed our corpus to include the same female speaker as the STUDIES teacher, acting as an operator in simulated phone calls. We describe a corpus construction methodology and analyze the recorded speech. We also conduct EDSS experiments using the CALLS and STUDIES corpora to investigate the effect of domain differences. The results show that mixing the two corpora during training causes biased improvements in the quality of synthetic speech due to the different degrees of expressiveness. Our project page of the corpus is http://sython.org/Corpus/STUDIES-2.

cs.SD↗

arXiv2023

ChatGPT-EDSS: Empathetic Dialogue Speech Synthesis Trained from ChatGPT-derived Context Word Embeddings

We propose ChatGPT-EDSS, an empathetic dialogue speech synthesis (EDSS) method using ChatGPT for extracting dialogue context. ChatGPT is a chatbot that can deeply understand the content and purpose of an input prompt and appropriately respond to the user's request. We focus on ChatGPT's reading comprehension and introduce it to EDSS, a task of synthesizing speech that can empathize with the interlocutor's emotion. Our method first gives chat history to ChatGPT and asks it to generate three words representing the intention, emotion, and speaking style for each line in the chat. Then, it trains an EDSS model using the embeddings of ChatGPT-derived context words as the conditioning features. The experimental results demonstrate that our method performs comparably to ones using emotion labels or neural network-derived context embeddings learned from chat histories. The collected ChatGPT-derived context information is available at https://sarulab-speech.github.io/demo_ChatGPT_EDSS/.

cs.SD↗

arXiv2023

JNV Corpus: A Corpus of Japanese Nonverbal Vocalizations with Diverse Phrases and Emotions

We present JNV (Japanese Nonverbal Vocalizations) corpus, a corpus of Japanese nonverbal vocalizations (NVs) with diverse phrases and emotions. Existing Japanese NV corpora lack phrase or emotion diversity, which makes it difficult to analyze NVs and support downstream tasks like emotion recognition. We first propose a corpus-design method that contains two phases: (1) collecting NVs phrases based on crowd-sourcing; (2) recording NVs by stimulating speakers with emotional scenarios. We then collect $420$ audio clips from $4$ speakers that cover $6$ emotions based on the proposed method. Results of comprehensive objective and subjective experiments demonstrate that the collected NVs have high emotion recognizability and authenticity that are comparable to previous corpora of English NVs. Additionally, we analyze the distributions of vowel types in Japanese NVs. To our best knowledge, JNV is currently the largest Japanese NVs corpus in terms of phrase and emotion diversities.

cs.SD↗

arXiv2023

Kernel-interpolation-based spatial active noise control with exterior radiation suppression

A spatial active noise control (ANC) method based on kernel interpolation of a sound field with exterior radiation suppression is proposed. The aim of spatial ANC is to reduce incoming noise over a target region by using multiple secondary sources and microphones. The method based on kernel interpolation of a sound field allows noise attenuation in a regional space with an array of arbitrary geometry. The cost function is defined as the acoustic potential energy, i.e., the regional integral of the power distribution inside the target region. However, this cost function does not take into consideration the exterior radiation of secondary sources. Thus, the acoustic power in the exterior region can be amplified by the output of the secondary sources. We propose two spatial ANC methods with exterior radiation suppression. The first approach is based on the minimization of the cost function formulated as a sum of the interior acoustic potential energy and exterior radiation power. The second approach is based on the minimization of the interior acoustic potential energy with inequality constraints on the exterior radiation power. Adaptive algorithms for minimizing the cost function are derived for the two approaches. Numerical experimental results indicate that the proposed methods can reduce the interior regional noise while suppressing the exterior radiation.

eess.AS↗

arXiv2023

Spatial Active Noise Control Method Based On Sound Field Interpolation From Reference Microphone Signals

A spatial active noise control (ANC) method based on the interpolation of a sound field from reference microphone signals is proposed. In most current spatial ANC methods, a sufficient number of error microphones are required to reduce noise over the target region because the sound field is estimated from error microphone signals. However, in practical applications, it is preferable that the number of error microphones is as small as possible to keep a space in the target region for ANC users. We propose to interpolate the sound field from reference microphones, which are normally placed outside the target region, instead of the error microphones. We derive a fixed filter for spatial noise reduction on the basis of the kernel ridge regression for sound field interpolation. Furthermore, to compensate for estimation errors, we combine the proposed fixed filter with multichannel ANC based on a transition of the control filter using the error microphone signals. Numerical experimental results indicate that regional noise can be sufficiently reduced by the proposed methods even when the number of error microphones is particularly small.

eess.AS↗

arXiv2023

Kernel interpolation of acoustic transfer functions with adaptive kernel for directed and residual reverberations

An interpolation method for region-to-region acoustic transfer functions (ATFs) based on kernel ridge regression with an adaptive kernel is proposed. Most current ATF interpolation methods do not incorporate the acoustic properties for which measurements are performed. Our proposed method is based on a separate adaptation of directional weighting functions to directed and residual reverberations, which are used for adapting kernel functions. Thus, the proposed method can not only impose constraints on fundamental acoustic properties, but can also adapt to the acoustic environment. Numerical experimental results indicated that our proposed method outperforms the current methods in terms of interpolation accuracy, especially at high frequencies.

eess.AS↗

arXiv2023

Duration-aware pause insertion using pre-trained language model for multi-speaker text-to-speech

Pause insertion, also known as phrase break prediction and phrasing, is an essential part of TTS systems because proper pauses with natural duration significantly enhance the rhythm and intelligibility of synthetic speech. However, conventional phrasing models ignore various speakers' different styles of inserting silent pauses, which can degrade the performance of the model trained on a multi-speaker speech corpus. To this end, we propose more powerful pause insertion frameworks based on a pre-trained language model. Our approach uses bidirectional encoder representations from transformers (BERT) pre-trained on a large-scale text corpus, injecting speaker embedding to capture various speaker characteristics. We also leverage duration-aware pause insertion for more natural multi-speaker TTS. We develop and evaluate two types of models. The first improves conventional phrasing models on the position prediction of respiratory pauses (RPs), i.e., silent pauses at word transitions without punctuation. It performs speaker-conditioned RP prediction considering contextual information and is used to demonstrate the effect of speaker information on the prediction. The second model is further designed for phoneme-based TTS models and performs duration-aware pause insertion, predicting both RPs and punctuation-indicated pauses (PIPs) that are categorized by duration. The evaluation results show that our models improve the precision and recall of pause insertion and the rhythm of synthetic speech.

eess.AS↗

arXiv2023

JaCappella Corpus: A Japanese a Cappella Vocal Ensemble Corpus

We construct a corpus of Japanese a cappella vocal ensembles (jaCappella corpus) for vocal ensemble separation and synthesis. It consists of 35 copyright-cleared vocal ensemble songs and their audio recordings of individual voice parts. These songs were arranged from out-of-copyright Japanese children's songs and have six voice parts (lead vocal, soprano, alto, tenor, bass, and vocal percussion). They are divided into seven subsets, each of which features typical characteristics of a music genre such as jazz and enka. The variety in genre and voice part match vocal ensembles recently widespread in social media services such as YouTube, although the main targets of conventional vocal ensemble datasets are choral singing made up of soprano, alto, tenor, and bass. Experimental evaluation demonstrates that our corpus is a challenging resource for vocal ensemble separation. Our corpus is available on our project page (https://tomohikonakamura.github.io/jaCappella_corpus/).

eess.AS↗

arXiv2022

Improving Speech Prosody of Audiobook Text-to-Speech Synthesis with Acoustic and Textual Contexts

We present a multi-speaker Japanese audiobook text-to-speech (TTS) system that leverages multimodal context information of preceding acoustic context and bilateral textual context to improve the prosody of synthetic speech. Previous work either uses unilateral or single-modality context, which does not fully represent the context information. The proposed method uses an acoustic context encoder and a textual context encoder to aggregate context information and feeds it to the TTS model, which enables the model to predict context-dependent prosody. We conducted comprehensive objective and subjective evaluations on a multi-speaker Japanese audiobook dataset. Experimental results demonstrate that the proposed method significantly outperforms two previous works. Additionally, we present insights about the different choices of context - modalities, lateral information and length - for audiobook TTS that have never been discussed in the literature before.

cs.SD↗

arXiv2022

Text-to-speech synthesis from dark data with evaluation-in-the-loop data selection

This paper proposes a method for selecting training data for text-to-speech (TTS) synthesis from dark data. TTS models are typically trained on high-quality speech corpora that cost much time and money for data collection, which makes it very challenging to increase speaker variation. In contrast, there is a large amount of data whose availability is unknown (a.k.a, "dark data"), such as YouTube videos. To utilize data other than TTS corpora, previous studies have selected speech data from the corpora on the basis of acoustic quality. However, considering that TTS models robust to data noise have been proposed, we should select data on the basis of its importance as training data to the given TTS model, not the quality of speech itself. Our method with a loop of training and evaluation selects training data on the basis of the automatically predicted quality of synthetic speech of a given TTS model. Results of evaluations using YouTube data reveal that our method outperforms the conventional acoustic-quality-based method.

cs.SD↗

arXiv2022

Mid-attribute speaker generation using optimal-transport-based interpolation of Gaussian mixture models

In this paper, we propose a method for intermediating multiple speakers' attributes and diversifying their voice characteristics in ``speaker generation,'' an emerging task that aims to synthesize a nonexistent speaker's naturally sounding voice. The conventional TacoSpawn-based speaker generation method represents the distributions of speaker embeddings by Gaussian mixture models (GMMs) conditioned with speaker attributes. Although this method enables the sampling of various speakers from the speaker-attribute-aware GMMs, it is not yet clear whether the learned distributions can represent speakers with an intermediate attribute (i.e., mid-attribute). To this end, we propose an optimal-transport-based method that interpolates the learned GMMs to generate nonexistent speakers with mid-attribute (e.g., gender-neutral) voices. We empirically validate our method and evaluate the naturalness of synthetic speech and the controllability of two speaker attributes: gender and language fluency. The evaluation results show that our method can control the generated speakers' attributes by a continuous scalar value without statistically significant degradation of speech naturalness.

cs.SD↗

arXiv2022

Visual onoma-to-wave: environmental sound synthesis from visual onomatopoeias and sound-source images

We propose a method for synthesizing environmental sounds from visually represented onomatopoeias and sound sources. An onomatopoeia is a word that imitates a sound structure, i.e., the text representation of sound. From this perspective, onoma-to-wave has been proposed to synthesize environmental sounds from the desired onomatopoeia texts. Onomatopoeias have another representation: visual-text representations of sounds in comics, advertisements, and virtual reality. A visual onomatopoeia (visual text of onomatopoeia) contains rich information that is not present in the text, such as a long-short duration of the image, so the use of this representation is expected to synthesize diverse sounds. Therefore, we propose visual onoma-to-wave for environmental sound synthesis from visual onomatopoeia. The method can transfer visual concepts of the visual text and sound-source image to the synthesized sound. We also propose a data augmentation method focusing on the repetition of onomatopoeias to enhance the performance of our method. An experimental evaluation shows that the methods can synthesize diverse environmental sounds from visual text and sound-source images.

cs.SD↗

arXiv2022

Hyperbolic Timbre Embedding for Musical Instrument Sound Synthesis Based on Variational Autoencoders

In this paper, we propose a musical instrument sound synthesis (MISS) method based on a variational autoencoder (VAE) that has a hierarchy-inducing latent space for timbre. VAE-based MISS methods embed an input signal into a low-dimensional latent representation that captures the characteristics of the input. Adequately manipulating this representation leads to sound morphing and timbre replacement. Although most VAE-based MISS methods seek a disentangled representation of pitch and timbre, how to capture an underlying structure in timbre remains an open problem. To address this problem, we focus on the fact that musical instruments can be hierarchically classified on the basis of their physical mechanisms. Motivated by this hierarchy, we propose a VAE-based MISS method by introducing a hyperbolic space for timbre. The hyperbolic space can represent treelike data more efficiently than the Euclidean space owing to its exponential growth property. Results of experiments show that the proposed method provides an efficient latent representation of timbre compared with the method using the Euclidean space.

eess.AS↗

arXiv2022

Multi-Task Adversarial Training Algorithm for Multi-Speaker Neural Text-to-Speech

We propose a novel training algorithm for a multi-speaker neural text-to-speech (TTS) model based on multi-task adversarial training. A conventional generative adversarial network (GAN)-based training algorithm significantly improves the quality of synthetic speech by reducing the statistical difference between natural and synthetic speech. However, the algorithm does not guarantee the generalization performance of the trained TTS model in synthesizing voices of unseen speakers who are not included in the training data. Our algorithm alternatively trains two deep neural networks: multi-task discriminator and multi-speaker neural TTS model (i.e., generator of GANs). The discriminator is trained not only to distinguish between natural and synthetic speech but also to verify the speaker of input speech is existent or non-existent (i.e., newly generated by interpolating seen speakers' embedding vectors). Meanwhile, the generator is trained to minimize the weighted sum of the speech reconstruction loss and adversarial loss for fooling the discriminator, which achieves high-quality multi-speaker TTS even if the target speaker is unseen. Experimental evaluation shows that our algorithm improves the quality of synthetic speech better than a conventional GANSpeech algorithm.

cs.SD↗

arXiv2022

Physics-informed convolutional neural network with bicubic spline interpolation for sound field estimation

A sound field estimation method based on a physics-informed convolutional neural network (PICNN) using spline interpolation is proposed. Most of the sound field estimation methods are based on wavefunction expansion, making the estimated function satisfy the Helmholtz equation. However, these methods rely only on physical properties; thus, they suffer from a significant deterioration of accuracy when the number of measurements is small. Recent learning-based methods based on neural networks have advantages in estimating from sparse measurements when training data are available. However, since physical properties are not taken into consideration, the estimated function can be a physically infeasible solution. We propose the application of PICNN to the sound field estimation problem by using a loss function that penalizes deviation from the Helmholtz equation. Since the output of CNN is a spatially discretized pressure distribution, it is difficult to directly evaluate the Helmholtz-equation loss function. Therefore, we incorporate bicubic spline interpolation in the PICNN framework. Experimental results indicated that accurate and physically feasible estimation from sparse measurements can be achieved with the proposed method.

cs.SD↗