arXiv subjects

Hiroshi Saruwatari

Publications and source records attributed to Hiroshi Saruwatari.

At least 37 records · Page 2Linked to original sources

arXiv2025

Emotional Text-To-Speech Based on Mutual-Information-Guided Emotion-Timbre Disentanglement

Current emotional Text-To-Speech (TTS) and style transfer methods rely on reference encoders to control global style or emotion vectors, but do not capture nuanced acoustic details of the reference speech. To this end, we propose a novel emotional TTS method that enables fine-grained phoneme-level emotion embedding prediction while disentangling intrinsic attributes of the reference speech. The proposed method employs a style disentanglement method to guide two feature extractors, reducing mutual information between timbre and emotion features, and effectively separating distinct style components from the reference speech. Experimental results demonstrate that our method outperforms baseline TTS systems in generating natural and emotionally rich speech. This work highlights the potential of disentangled and fine-grained representations in advancing the quality and flexibility of emotional TTS systems.

cs.SD↗

arXiv2025

Drum-to-Vocal Percussion Sound Conversion and Its Evaluation Methodology

This paper defines the novel task of drum-to-vocal percussion (VP) sound conversion. VP imitates percussion instruments through human vocalization and is frequently employed in contemporary a cappella music. It exhibits acoustic properties distinct from speech and singing (e.g., aperiodicity, noisy transients, and the absence of linguistic structure), making conventional speech or singing synthesis methods unsuitable. We thus formulate VP synthesis as a timbre transfer problem from drum sounds, leveraging their rhythmic and timbral correspondence. To support this formulation, we define three requirements for successful conversion: rhythmic fidelity, timbral consistency, and naturalness as VP. We also propose corresponding subjective evaluation criteria. We implement two baseline conversion methods using a neural audio synthesizer, the real-time audio variational autoencoder (RAVE), with and without vector quantization (VQ). Subjective experiments show that both methods produce plausible VP outputs, with the VQ-based RAVE model yielding more consistent conversion.

cs.SD↗

arXiv2025

Spatial-CLAP: Learning Spatially-Aware audio--text Embeddings for Multi-Source Conditions

Contrastive language--audio pretraining (CLAP) has achieved remarkable success as an audio--text embedding framework, but existing approaches are limited to monaural or single-source conditions and cannot fully capture spatial information. The central challenge in modeling spatial information lies in multi-source conditions, where the correct correspondence between each sound source and its location is required. To tackle this problem, we propose Spatial-CLAP, which introduces a content-aware spatial encoder that enables spatial representations coupled with audio content. We further propose spatial contrastive learning (SCL), a training strategy that explicitly enforces the learning of the correct correspondence and promotes more reliable embeddings under multi-source conditions. Experimental evaluations, including downstream tasks, demonstrate that Spatial-CLAP learns effective embeddings even under multi-source conditions, and confirm the effectiveness of SCL. Moreover, evaluation on unseen three-source mixtures highlights the fundamental distinction between conventional single-source training and our proposed multi-source training paradigm. These findings establish a new paradigm for spatially-aware audio--text embeddings.

cs.SD↗

arXiv2025

Analysing the Language of Neural Audio Codecs

This study presents a comparative analysis of the statistical and linguistic properties of neural audio codecs (NACs). We investigate discrete speech tokens produced by various NAC models, examining their adherence to linguistic statistical laws such as Zipf's law and Heaps' law, as well as their entropy and redundancy. To assess how these token-level properties relate to semantic and acoustic preservation in synthesized speech, we evaluate intelligibility using error rates of automatic speech recognition, and quality using the UTMOS score. Our results reveal that NAC tokens, particularly 3-grams, exhibit language-like statistical patterns. Moreover, these properties, together with measures of information content, are found to correlate with improved performances in speech recognition and resynthesis tasks. These findings offer insights into the structure of NAC token sequences and inform the design of more effective generative speech models.

cs.CL↗

arXiv2025

Speaker-Conditioned Phrase Break Prediction for Text-to-Speech with Phoneme-Level Pre-trained Language Model

This paper advances phrase break prediction (also known as phrasing) in multi-speaker text-to-speech (TTS) systems. We integrate speaker-specific features by leveraging speaker embeddings to enhance the performance of the phrasing model. We further demonstrate that these speaker embeddings can capture speaker-related characteristics solely from the phrasing task. Besides, we explore the potential of pre-trained speaker embeddings for unseen speakers through a few-shot adaptation method. Furthermore, we pioneer the application of phoneme-level pre-trained language models to this TTS front-end task, which significantly boosts the accuracy of the phrasing model. Our methods are rigorously assessed through both objective and subjective evaluations, demonstrating their effectiveness.

eess.AS↗

arXiv2025

Multi-Sampling-Frequency Naturalness MOS Prediction Using Self-Supervised Learning Model with Sampling-Frequency-Independent Layer

We introduce our submission to the AudioMOS Challenge (AMC) 2025 Track 3: mean opinion score (MOS) prediction for speech with multiple sampling frequencies (SFs). Our submitted model integrates an SF-independent (SFI) convolutional layer into a self-supervised learning (SSL) model to achieve SFI speech feature extraction for MOS prediction. We present some strategies to improve the MOS prediction performance of our model: distilling knowledge from a pretrained non-SFI-SSL model and pretraining with a large-scale MOS dataset. Our submission to the AMC 2025 Track 3 ranked the first in one evaluation metric and the fourth in the final ranking. We also report the results of our ablation study to investigate essential factors of our model.

cs.SD↗

arXiv2025

Hyperbolic Embeddings for Order-Aware Classification of Audio Effect Chains

Audio effects (AFXs) are essential tools in music production, frequently applied in chains to shape timbre and dynamics. The order of AFXs in a chain plays a crucial role in determining the final sound, particularly when non-linear (e.g., distortion) or time-variant (e.g., chorus) processors are involved. Despite its importance, most AFX-related studies have primarily focused on estimating effect types and their parameters from a wet signal. To address this gap, we formulate AFX chain recognition as the task of jointly estimating AFX types and their order from a wet signal. We propose a neural-network-based method that embeds wet signals into a hyperbolic space and classifies their AFX chains. Hyperbolic space can represent tree-structured data more efficiently than Euclidean space due to its exponential expansion property. Since AFX chains can be represented as trees, with AFXs as nodes and edges encoding effect order, hyperbolic space is well-suited for modeling the exponentially growing and non-commutative nature of ordered AFX combinations, where changes in effect order can result in different final sounds. Experiments using guitar sounds demonstrate that, with an appropriate curvature, the proposed method outperforms its Euclidean counterpart. Further analysis based on AFX type and chain length highlights the effectiveness of the proposed method in capturing AFX order.

cs.SD↗

arXiv2025

Active Learning for Text-to-Speech Synthesis with Informative Sample Collection

The construction of high-quality datasets is a cornerstone of modern text-to-speech (TTS) systems. However, the increasing scale of available data poses significant challenges, including storage constraints. To address these issues, we propose a TTS corpus construction method based on active learning. Unlike traditional feed-forward and model-agnostic corpus construction approaches, our method iteratively alternates between data collection and model training, thereby focusing on acquiring data that is more informative for model improvement. This approach enables the construction of a data-efficient corpus. Experimental results demonstrate that the corpus constructed using our method enables higher-quality speech synthesis than corpora of the same size.

cs.SD↗

arXiv2025

RELATE: Subjective evaluation dataset for automatic evaluation of relevance between text and audio

In text-to-audio (TTA) research, the relevance between input text and output audio is an important evaluation aspect. Traditionally, it has been evaluated from both subjective and objective perspectives. However, subjective evaluation is costly in terms of money and time, and objective evaluation is unclear regarding the correlation to subjective evaluation scores. In this study, we construct RELATE, an open-sourced dataset that subjectively evaluates the relevance. Also, we benchmark a model for automatically predicting the subjective evaluation score from synthesized audio. Our model outperforms a conventional CLAPScore model, and that trend extends to many sound categories.

cs.SD↗

arXiv2025

Local Equivariance Error-Based Metrics for Evaluating Sampling-Frequency-Independent Property of Neural Network

Audio signal processing methods based on deep neural networks (DNNs) are typically trained only at a single sampling frequency (SF) and therefore require signal resampling to handle untrained SFs. However, recent studies have shown that signal resampling can degrade performance with untrained SFs. This problem has been overlooked because most studies evaluate only the performance at trained SFs. In this paper, to assess the robustness of DNNs to SF changes, which we refer to as the SF-independent (SFI) property, we propose three metrics to quantify the SFI property on the basis of local equivariance error (LEE). LEE measures the robustness of DNNs to input transformations. By using signal resampling as input transformation, we extend LEE to measure the robustness of audio source separation methods to signal resampling. The proposed metrics are constructed to quantify the SFI property in specific network components responsible for predicting time-frequency masks. Experiments on music source separation demonstrated a strong correlation between the proposed metrics and performance degradation at untrained SFs.

cs.SD↗

arXiv2024

Causal Speech Enhancement with Predicting Semantics based on Quantized Self-supervised Learning Features

Real-time speech enhancement (SE) is essential to online speech communication. Causal SE models use only the previous context while predicting future information, such as phoneme continuation, may help performing causal SE. The phonetic information is often represented by quantizing latent features of self-supervised learning (SSL) models. This work is the first to incorporate SSL features with causality into an SE model. The causal SSL features are encoded and combined with spectrogram features using feature-wise linear modulation to estimate a mask for enhancing the noisy input speech. Simultaneously, we quantize the causal SSL features using vector quantization to represent phonetic characteristics as semantic tokens. The model not only encodes SSL features but also predicts the future semantic tokens in multi-task learning (MTL). The experimental results using VoiceBank + DEMAND dataset show that our proposed method achieves 2.88 in PESQ, especially with semantic prediction MTL, in which we confirm that the semantic prediction played an important role in causal SE.

eess.AS↗

arXiv2024

DNN-based ensemble singing voice synthesis with interactions between singers

We propose a singing voice synthesis (SVS) method for a more unified ensemble singing voice by modeling interactions between singers. Most existing SVS methods aim to synthesize a solo voice, and do not consider interactions between singers, i.e., adjusting one's own voice to the others' voices. Since the production of ensemble voices from solo singing voices ignores the interactions, it can degrade the unity of the vocal ensemble. Therefore, we propose a SVS that reproduces the interactions. It is based on an architecture that uses musical scores of multiple voice parts, and loss functions that simulate the interactions' effect to acoustic features. Experimental results show that our methods improve the unity of the vocal ensemble.

eess.AS↗

arXiv2024

The T05 System for The VoiceMOS Challenge 2024: Transfer Learning from Deep Image Classifier to Naturalness MOS Prediction of High-Quality Synthetic Speech

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.

cs.SD↗

arXiv2024

Cross-Dialect Text-To-Speech in Pitch-Accent Language Incorporating Multi-Dialect Phoneme-Level BERT

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.

cs.SD↗

arXiv2024

BigCodec: Pushing the Limits of Low-Bitrate Neural Speech Codec

We present BigCodec, a low-bitrate neural speech codec. While recent neural speech codecs have shown impressive progress, their performance significantly deteriorates at low bitrates (around 1 kbps). Although a low bitrate inherently restricts performance, other factors, such as model capacity, also hinder further improvements. To address this problem, we scale up the model size to 159M parameters that is more than 10 times larger than popular codecs with about 10M parameters. Besides, we integrate sequential models into traditional convolutional architectures to better capture temporal dependency and adopt low-dimensional vector quantization to ensure a high code utilization. Comprehensive objective and subjective evaluations show that BigCodec, with a bitrate of 1.04 kbps, significantly outperforms several existing low-bitrate codecs. Furthermore, BigCodec achieves objective performance comparable to popular codecs operating at 4-6 times higher bitrates, and even delivers better subjective perceptual quality than the ground truth.

eess.AS↗

arXiv2024

SpeechBERTScore: Reference-Aware Automatic Evaluation of Speech Generation Leveraging NLP Evaluation Metrics

While subjective assessments have been the gold standard for evaluating speech generation, there is a growing need for objective metrics that are highly correlated with human subjective judgments due to their cost efficiency. This paper proposes reference-aware automatic evaluation methods for speech generation inspired by evaluation metrics in natural language processing. The proposed SpeechBERTScore computes the BERTScore for self-supervised dense speech features of the generated and reference speech, which can have different sequential lengths. We also propose SpeechBLEU and SpeechTokenDistance, which are computed on speech discrete tokens. The evaluations on synthesized speech show that our method correlates better with human subjective ratings than mel cepstral distortion and a recent mean opinion score prediction model. Also, they are effective in noisy speech evaluation and have cross-lingual applicability.

cs.SD↗

arXiv2024

SaSLaW: Dialogue Speech Corpus with Audio-visual Egocentric Information Toward Environment-adaptive Dialogue Speech Synthesis

This paper presents SaSLaW, a spontaneous dialogue speech corpus containing synchronous recordings of what speakers speak, listen to, and watch. Humans consider the diverse environmental factors and then control the features of their utterances in face-to-face voice communications. Spoken dialogue systems capable of this adaptation to these audio environments enable natural and seamless communications. SaSLaW was developed to model human-speech adjustment for audio environments via first-person audio-visual perceptions in spontaneous dialogues. We propose the construction methodology of SaSLaW and display the analysis result of the corpus. We additionally conducted an experiment to develop text-to-speech models using SaSLaW and evaluate their performance of adaptations to audio environments. The results indicate that models incorporating hearing-audio data output more plausible speech tailored to diverse audio environments than the vanilla text-to-speech model.

eess.AS↗

arXiv2024

Spatial Voice Conversion: Voice Conversion Preserving Spatial Information and Non-target Signals

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.

cs.SD↗