Search

Fashion aesthetic evaluation is the task of estimating how well the outfits worn by individuals in images suit them. In this work, we examine the zero-shot performance of GPT-4V on this task for the first time. We show that its predictions align fairly well with human judgments on our datasets, and also find that it struggles with ranking outfits in similar colors. The code is available at https://github.com/st-tech/gpt4v-fashion-aesthetic-evaluation.

Some datasets with the described content and order of occurrence of sounds have been released for conversion between environmental sound and text. However, there are very few texts that include information on the impressions humans feel, such as "sharp" and "gorgeous," when they hear environmental sounds. In this study, we constructed a dataset with impression captions for environmental sounds that describe the impressions humans have when hearing these sounds. We used ChatGPT to generate impression captions and selected the most appropriate captions for sound by humans. Our dataset consists of 3,600 impression captions for environmental sounds. To evaluate the appropriateness of impression captions for environmental sounds, we conducted subjective and objective evaluations. From our evaluation results, we indicate that appropriate impression captions for environmental sounds can be generated.

Recent research on explainable recommendation generally frames the task as a standard text generation problem, and evaluates models simply based on the textual similarity between the predicted and ground-truth explanations. However, this approach fails to consider one crucial aspect of the systems: whether their outputs accurately reflect the users' (post-purchase) sentiments, i.e., whether and why they would like and/or dislike the recommended items. To shed light on this issue, we introduce new datasets and evaluation methods that focus on the users' sentiments. Specifically, we construct the datasets by explicitly extracting users' positive and negative opinions from their post-purchase reviews using an LLM, and propose to evaluate systems based on whether the generated explanations 1) align well with the users' sentiments, and 2) accurately identify both positive and negative opinions of users on the target items. We benchmark several recent models on our datasets and demonstrate that achieving strong performance on existing metrics does not ensure that the generated explanations align well with the users' sentiments. Lastly, we find that existing models can provide more sentiment-aware explanations when the users' (predicted) ratings for the target items are directly fed into the models as input. We will release our code and datasets upon acceptance.

We present our system (denoted as T05) for the VoiceMOS Challenge (VMC) 2024. Our system was designed for the VMC 2024 Track 1, which focused on the accurate prediction of naturalness mean opinion score (MOS) for high-quality synthetic speech. In addition to a pretrained self-supervised learning (SSL)-based speech feature extractor, our system incorporates a pretrained image feature extractor to capture the difference of synthetic speech observed in speech spectrograms. We first separately train two MOS predictors that use either of an SSL-based or spectrogram-based feature. Then, we fine-tune the two predictors for better MOS prediction using the fusion of two extracted features. In the VMC 2024 Track 1, our T05 system achieved first place in 7 out of 16 evaluation metrics and second place in the remaining 9 metrics, with a significant difference compared to those ranked third and below. We also report the results of our ablation study to investigate essential factors of our system., Comment: Accepted by IEEE SLT 2024. Our MOS prediction system (UTMOSv2) is available in https://github.com/sarulab-speech/UTMOSv2

We explore cross-dialect text-to-speech (CD-TTS), a task to synthesize learned speakers' voices in non-native dialects, especially in pitch-accent languages. CD-TTS is important for developing voice agents that naturally communicate with people across regions. We present a novel TTS model comprising three sub-modules to perform competitively at this task. We first train a backbone TTS model to synthesize dialect speech from a text conditioned on phoneme-level accent latent variables (ALVs) extracted from speech by a reference encoder. Then, we train an ALV predictor to predict ALVs tailored to a target dialect from input text leveraging our novel multi-dialect phoneme-level BERT. We conduct multi-dialect TTS experiments and evaluate the effectiveness of our model by comparing it with a baseline derived from conventional dialect TTS methods. The results show that our model improves the dialectal naturalness of synthetic speech in CD-TTS., Comment: Accepted by IEEE SLT 2024

In this work, we propose a fashion item recommendation model that incorporates hyperbolic geometry into user and item representations. Using hyperbolic space, our model aims to capture implicit hierarchies among items based on their visual data and users' purchase history. During training, we apply a multi-task learning framework that considers both hyperbolic and Euclidean distances in the loss function. Our experiments on three data sets show that our model performs better than previous models trained in Euclidean space only, confirming the effectiveness of our model. Our ablation studies show that multi-task learning plays a key role, and removing the Euclidean loss substantially deteriorates the model performance., Comment: This work was presented at the CVFAD Workshop at CVPR 2024

Spoken dialogue plays a crucial role in human-AI interactions, necessitating dialogue-oriented spoken language models (SLMs). To develop versatile SLMs, large-scale and diverse speech datasets are essential. Additionally, to ensure hiqh-quality speech generation, the data must be spontaneous like in-wild data and must be acoustically clean with noise removed. Despite the critical need, no open-source corpus meeting all these criteria has been available. This study addresses this gap by constructing and releasing a large-scale spoken dialogue corpus, named Japanese Corpus for Human-AI Talks (J-CHAT), which is publicly accessible. Furthermore, this paper presents a language-independent method for corpus construction and describes experiments on dialogue generation using SLMs trained on J-CHAT. Experimental results indicate that the collected data from multiple domains by our method improve the naturalness and meaningfulness of dialogue generation., Comment: 8 pages, 6 figures

This paper proposes a new task called spatial voice conversion, which aims to convert a target voice while preserving spatial information and non-target signals. Traditional voice conversion methods focus on single-channel waveforms, ignoring the stereo listening experience inherent in human hearing. Our baseline approach addresses this gap by integrating blind source separation (BSS), voice conversion (VC), and spatial mixing to handle multi-channel waveforms. Through experimental evaluations, we organize and identify the key challenges inherent in this task, such as maintaining audio quality and accurately preserving spatial information. Our results highlight the fundamental difficulties in balancing these aspects, providing a benchmark for future research in spatial voice conversion. The proposed method's code is publicly available to encourage further exploration in this domain., Comment: Accepted to Interspeech 2024

We propose noise-robust voice conversion (VC) which takes into account the recording quality and environment of noisy source speech. Conventional denoising training improves the noise robustness of a VC model by learning noisy-to-clean VC process. However, the naturalness of the converted speech is limited when the noise of the source speech is unseen during the training. To this end, our proposed training conditions a VC model on two latent variables representing the recording quality and environment of the source speech. These latent variables are derived from deep neural networks pre-trained on recording quality assessment and acoustic scene classification and calculated in an utterance-wise or frame-wise manner. As a result, the trained VC model can explicitly learn information about speech degradation during the training. Objective and subjective evaluations show that our training improves the quality of the converted speech compared to the conventional training., Comment: 5 pages, accepted for INTERSPEECH 2024, audio samples: http://y-saito.sakura.ne.jp/sython/Corpus/SRC4VC/IS2024_CDT_supplementary/demo_cdt.html

We present SRC4VC, a new corpus containing 11 hours of speech recorded on smartphones by 100 Japanese speakers. Although high-quality multi-speaker corpora can advance voice conversion (VC) technologies, they are not always suitable for testing VC when low-quality speech recording is given as the input. To this end, we first asked 100 crowdworkers to record their voice samples using smartphones. Then, we annotated the recorded samples with speaker-wise recording-quality scores and utterance-wise perceived emotion labels. We also benchmark SRC4VC on any-to-any VC, in which we trained a multi-speaker VC model on high-quality speech and used the SRC4VC speakers' voice samples as the source in VC. The results show that the recording quality mismatch between the training and evaluation data significantly degrades the VC performance, which can be improved by applying speech enhancement to the low-quality source speech samples., Comment: Accepted for INTERSPEECH 2024, corpus project page: https://y-saito.sakura.ne.jp/sython/Corpus/SRC4VC/index.html

Techniques that explain the predictions of black-box machine learning models are crucial to make the models transparent, thereby increasing trust in AI systems. The input features to the models often have a nested structure that consists of high- and low-level features, and each high-level feature is decomposed into multiple low-level features. For such inputs, both high-level feature attributions (HiFAs) and low-level feature attributions (LoFAs) are important for better understanding the model's decision. In this paper, we propose a model-agnostic local explanation method that effectively exploits the nested structure of the input to estimate the two-level feature attributions simultaneously. A key idea of the proposed method is to introduce the consistency property that should exist between the HiFAs and LoFAs, thereby bridging the separate optimization problems for estimating them. Thanks to this consistency property, the proposed method can produce HiFAs and LoFAs that are both faithful to the black-box models and consistent with each other, using a smaller number of queries to the models. In experiments on image classification in multiple instance learning and text classification using language models, we demonstrate that the HiFAs and LoFAs estimated by the proposed method are accurate, faithful to the behaviors of the black-box models, and provide consistent explanations.

Conventional machine learning algorithms have traditionally been designed under the assumption that input data follows a vector-based format, with an emphasis on vector-centric paradigms. However, as the demand for tasks involving set-based inputs has grown, there has been a paradigm shift in the research community towards addressing these challenges. In recent years, the emergence of neural network architectures such as Deep Sets and Transformers has presented a significant advancement in the treatment of set-based data. These architectures are specifically engineered to naturally accommodate sets as input, enabling more effective representation and processing of set structures. Consequently, there has been a surge of research endeavors dedicated to exploring and harnessing the capabilities of these architectures for various tasks involving the approximation of set functions. This comprehensive survey aims to provide an overview of the diverse problem settings and ongoing research efforts pertaining to neural networks that approximate set functions. By delving into the intricacies of these approaches and elucidating the associated challenges, the survey aims to equip readers with a comprehensive understanding of the field. Through this comprehensive perspective, we hope that researchers can gain valuable insights into the potential applications, inherent limitations, and future directions of set-based neural networks. Indeed, from this survey we gain two insights: i) Deep Sets and its variants can be generalized by differences in the aggregation function, and ii) the behavior of Deep Sets is sensitive to the choice of the aggregation function. From these observations, we show that Deep Sets, one of the well-known permutation-invariant neural networks, can be generalized in the sense of a quasi-arithmetic mean.

We present UTDUSS, the UTokyo-SaruLab system submitted to Interspeech2024 Speech Processing Using Discrete Speech Unit Challenge. The challenge focuses on using discrete speech unit learned from large speech corpora for some tasks. We submitted our UTDUSS system to two text-to-speech tracks: Vocoder and Acoustic+Vocoder. Our system incorporates neural audio codec (NAC) pre-trained on only speech corpora, which makes the learned codec represent rich acoustic features that are necessary for high-fidelity speech reconstruction. For the acoustic+vocoder track, we trained an acoustic model based on Transformer encoder-decoder that predicted the pre-trained NAC tokens from text input. We describe our strategies to build these models, such as data selection, downsampling, and hyper-parameter tuning. Our system ranked in second and first for the Vocoder and Acoustic+Vocoder tracks, respectively., Comment: 5 pages, 3 figures

In text-to-speech synthesis, the ability to control voice characteristics is vital for various applications. By leveraging thriving text prompt-based generation techniques, it should be possible to enhance the nuanced control of voice characteristics. While previous research has explored the prompt-based manipulation of voice characteristics, most studies have used pre-recorded speech, which limits the diversity of voice characteristics available. Thus, we aim to address this gap by creating a novel corpus and developing a model for prompt-based manipulation of voice characteristics in text-to-speech synthesis, facilitating a broader range of voice characteristics. Specifically, we propose a method to build a sizable corpus pairing voice characteristics descriptions with corresponding speech samples. This involves automatically gathering voice-related speech data from the Internet, ensuring its quality, and manually annotating it using crowdsourcing. We implement this method with Japanese language data and analyze the results to validate its effectiveness. Subsequently, we propose a construction method of the model to retrieve speech from voice characteristics descriptions based on a contrastive learning method. We train the model using not only conservative contrastive learning but also feature prediction learning to predict quantitative speech features corresponding to voice characteristics. We evaluate the model performance via experiments with the corpus we constructed above., Comment: Submitted to IEEE/ACM Transactions on Audio, Speech, and Language Processing. arXiv admin note: text overlap with arXiv:2309.13509

Developing Text-to-Speech (TTS) systems that can synthesize natural breath is essential for human-like voice agents but requires extensive manual annotation of breath positions in training data. To this end, we propose a self-training method for training a breath detection model that can automatically detect breath positions in speech. Our method trains the model using a large speech corpus and involves: 1) annotation of limited breath sounds utilizing a rule-based approach, and 2) iterative augmentation of these annotations through pseudo-labeling based on the model's predictions. Our detection model employs Conformer blocks with down-/up-sampling layers, enabling accurate frame-wise breath detection. We investigate its effectiveness in multi-speaker TTS using text transcripts with detected breath marks. The results indicate that using our proposed model for breath detection and breath mark insertion synthesizes breath-contained speech more naturally than a baseline model., Comment: Accepted by INTERSPEECH2024

We propose StyleCap, a method to generate natural language descriptions of speaking styles appearing in speech. Although most of conventional techniques for para-/non-linguistic information recognition focus on the category classification or the intensity estimation of pre-defined labels, they cannot provide the reasoning of the recognition result in an interpretable manner. StyleCap is a first step towards an end-to-end method for generating speaking-style prompts from speech, i.e., automatic speaking-style captioning. StyleCap is trained with paired data of speech and natural language descriptions. We train neural networks that convert a speech representation vector into prefix vectors that are fed into a large language model (LLM)-based text decoder. We explore an appropriate text decoder and speech feature representation suitable for this new task. The experimental results demonstrate that our StyleCap leveraging richer LLMs for the text decoder, speech self-supervised learning (SSL) features, and sentence rephrasing augmentation improves the accuracy and diversity of generated speaking-style captions. Samples of speaking-style captions generated by our StyleCap are publicly available., Comment: Accepted for ICASSP2024

We present the JVNV, a Japanese emotional speech corpus with verbal content and nonverbal vocalizations whose scripts are generated by a large-scale language model. Existing emotional speech corpora lack not only proper emotional scripts but also nonverbal vocalizations (NVs) that are essential expressions in spoken language to express emotions. We propose an automatic script generation method to produce emotional scripts by providing seed words with sentiment polarity and phrases of nonverbal vocalizations to ChatGPT using prompt engineering. We select 514 scripts with balanced phoneme coverage from the generated candidate scripts with the assistance of emotion confidence scores and language fluency scores. We demonstrate the effectiveness of JVNV by showing that JVNV has better phoneme coverage and emotion recognizability than previous Japanese emotional speech corpora. We then benchmark JVNV on emotional text-to-speech synthesis using discrete codes to represent NVs. We show that there still exists a gap between the performance of synthesizing read-aloud speech and emotional speech, and adding NVs in the speech makes the task even harder, which brings new challenges for this task and makes JVNV a valuable resource for relevant works in the future. To our best knowledge, JVNV is the first speech corpus that generates scripts automatically using large language models.

In text-to-speech, controlling voice characteristics is important in achieving various-purpose speech synthesis. Considering the success of text-conditioned generation, such as text-to-image, free-form text instruction should be useful for intuitive and complicated control of voice characteristics. A sufficiently large corpus of high-quality and diverse voice samples with corresponding free-form descriptions can advance such control research. However, neither an open corpus nor a scalable method is currently available. To this end, we develop Coco-Nut, a new corpus including diverse Japanese utterances, along with text transcriptions and free-form voice characteristics descriptions. Our methodology to construct this corpus consists of 1) automatic collection of voice-related audio data from the Internet, 2) quality assurance, and 3) manual annotation using crowdsourcing. Additionally, we benchmark our corpus on the prompt embedding model trained by contrastive speech-text learning., Comment: Submitted to ASRU2023

We propose {\it HumanDiffusion,} a diffusion model trained from humans' perceptual gradients to learn an acceptable range of data for humans (i.e., human-acceptable distribution). Conventional HumanGAN aims to model the human-acceptable distribution wider than the real-data distribution by training a neural network-based generator with human-based discriminators. However, HumanGAN training tends to converge in a meaningless distribution due to the gradient vanishing or mode collapse and requires careful heuristics. In contrast, our HumanDiffusion learns the human-acceptable distribution through Langevin dynamics based on gradients of human perceptual evaluations. Our training iterates a process to diffuse real data to cover a wider human-acceptable distribution and can avoid the issues in the HumanGAN training. The evaluation results demonstrate that our HumanDiffusion can successfully represent the human-acceptable distribution without any heuristics for the training., Comment: Proceedings of INTERSPEECH

Identifying the relationship between healthcare attributes, lifestyles, and personality is vital for understanding and improving physical and mental well-being. Machine learning approaches are promising for modeling their relationships and offering actionable suggestions. In this paper, we propose Virtual Human Generative Model (VHGM), a machine learning model for estimating healthcare, lifestyles, and personality attributes. VHGM is a deep generative model trained with masked modeling to learn the joint distribution of attributes conditioned on known ones. Using heterogeneous tabular datasets, VHGM learns more than 2,000 attributes efficiently. We numerically evaluate the performance of VHGM and its training techniques and have deployed VHGM as a Web service, enabling various healthcare applications., Comment: 19 pages, 4 figures

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/., Comment: 5 pages, accepted for INTERSPEECH 2023

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., Comment: 5 pages, accepted for INTERSPEECH2023

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., Comment: Accepted by ICASSP2023

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., Comment: Submitted to ICASSP 2023. Demo: https://sarulab-speech.github.io/demo_mid-attribute-speaker-generation

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., Comment: 6 pages, 1 figure, Accepted for APSIPA ASC 2022

This paper proposes a human-in-the-loop speaker-adaptation method for multi-speaker text-to-speech. With a conventional speaker-adaptation method, a target speaker's embedding vector is extracted from his/her reference speech using a speaker encoder trained on a speaker-discriminative task. However, this method cannot obtain an embedding vector for the target speaker when the reference speech is unavailable. Our method is based on a human-in-the-loop optimization framework, which incorporates a user to explore the speaker-embedding space to find the target speaker's embedding. The proposed method uses a sequential line search algorithm that repeatedly asks a user to select a point on a line segment in the embedding space. To efficiently choose the best speech sample from multiple stimuli, we also developed a system in which a user can switch between multiple speakers' voices for each phoneme while looping an utterance. Experimental results indicate that the proposed method can achieve comparable performance to the conventional one in objective and subjective evaluations even if reference speech is not used as the input of a speaker encoder directly., Comment: 5 pages, 3 figures, Accepted for INTERSPEECH2022

We propose an end-to-end empathetic dialogue speech synthesis (DSS) model that considers both the linguistic and prosodic contexts of dialogue history. Empathy is the active attempt by humans to get inside the interlocutor in dialogue, and empathetic DSS is a technology to implement this act in spoken dialogue systems. Our model is conditioned by the history of linguistic and prosody features for predicting appropriate dialogue context. As such, it can be regarded as an extension of the conventional linguistic-feature-based dialogue history modeling. To train the empathetic DSS model effectively, we investigate 1) a self-supervised learning model pretrained with large speech corpora, 2) a style-guided training using a prosody embedding of the current utterance to be predicted by the dialogue context embedding, 3) a cross-modal attention to combine text and speech modalities, and 4) a sentence-wise embedding to achieve fine-grained prosody modeling rather than utterance-wise modeling. The evaluation results demonstrate that 1) simply considering prosodic contexts of the dialogue history does not improve the quality of speech in empathetic DSS and 2) introducing style-guided training and sentence-wise embedding modeling achieves higher speech quality than that by the conventional method., Comment: 5 pages, 3 figures, Accepted for INTERSPEECH2022

We present STUDIES, a new speech corpus for developing a voice agent that can speak in a friendly manner. Humans naturally control their speech prosody to empathize with each other. By incorporating this "empathetic dialogue" behavior into a spoken dialogue system, we can develop a voice agent that can respond to a user more naturally. We designed the STUDIES corpus to include a speaker who speaks with empathy for the interlocutor's emotion explicitly. We describe our methodology to construct an empathetic dialogue speech corpus and report the analysis results of the STUDIES corpus. We conducted a text-to-speech experiment to initially investigate how we can develop more natural voice agent that can tune its speaking style corresponding to the interlocutor's emotion. The results show that the use of interlocutor's emotion label and conversational context embedding can produce speech with the same degree of naturalness as that synthesized by using the agent's emotion label. Our project page of the STUDIES corpus is http://sython.org/Corpus/STUDIES., Comment: 5 pages, 2 figures, Accepted for INTERSPEECH2022, project page: http://sython.org/Corpus/STUDIES