Do learned speech symbols follow Zipf's law?

In this study, we investigate whether speech symbols, learned through deep learning, follow Zipf's law, akin to natural language symbols. Zipf's law is an empirical law that delineates the frequency distribution of words, forming fundamentals for statistical analysis in natural language processing. Natural language symbols, which are invented by humans to symbolize speech content, are recognized to comply with this law. On the other hand, recent breakthroughs in spoken language processing have given rise to the development of learned speech symbols; these are data-driven symbolizations of speech content. Our objective is to ascertain whether these data-driven speech symbols follow Zipf's law, as the same as natural language symbols. Through our investigation, we aim to forge new ways for the statistical analysis of spoken language processing.

Diversity-based core-set selection for text-to-speech with linguistic and acoustic features

This paper proposes a method for extracting a lightweight subset from a text-to-speech (TTS) corpus ensuring synthetic speech quality. In recent years, methods have been proposed for constructing large-scale TTS corpora by collecting diverse data from massive sources such as audiobooks and YouTube. Although these methods have gained significant attention for enhancing the expressive capabilities of TTS systems, they often prioritize collecting vast amounts of data without considering practical constraints like storage capacity and computation time in training, which limits the available data quantity. Consequently, the need arises to efficiently collect data within these volume constraints. To address this, we propose a method for selecting the core subset~(known as \textit{core-set}) from a TTS corpus on the basis of a \textit{diversity metric}, which measures the degree to which a subset encompasses a wide range. Experimental results demonstrate that our proposed method performs significantly better than the baseline phoneme-balanced data selection across language and corpus size.

Kernel Interpolation of Incident Sound Field in Region Including Scattering Objects

A method for estimating the incident sound field inside a region containing scattering objects is proposed. The sound field estimation method has various applications, such as spatial audio capturing and spatial active noise control; however, most existing methods do not take into account the presence of scatterers within the target estimation region. Although several techniques exist that employ knowledge or measurements of the properties of the scattering objects, it is usually difficult to obtain them precisely in advance, and their properties may change during the estimation process. Our proposed method is based on the kernel ridge regression of the incident field, with a separation from the scattering field represented by a spherical wave function expansion, thus eliminating the need for prior modeling or measurements of the scatterers. Moreover, we introduce a weighting matrix to induce smoothness of the scattering field in the angular direction, which alleviates the effect of the truncation order of the expansion coefficients on the estimation accuracy. Experimental results indicate that the proposed method achieves a higher level of estimation accuracy than the kernel ridge regression without separation.

Perceptual Quality Enhancement of Sound Field Synthesis Based on Combination of Pressure and Amplitude Matching

A sound field synthesis method enhancing perceptual quality is proposed. Sound field synthesis using multiple loudspeakers enables spatial audio reproduction with a broad listening area; however, synthesis errors at high frequencies called spatial aliasing artifacts are unavoidable. To minimize these artifacts, we propose a method based on the combination of pressure and amplitude matching. On the basis of the human's auditory properties, synthesizing the amplitude distribution will be sufficient for horizontal sound localization. Furthermore, a flat amplitude response should be synthesized as much as possible to avoid coloration. Therefore, we apply amplitude matching, which is a method to synthesize the desired amplitude distribution with arbitrary phase distribution, for high frequencies and conventional pressure matching for low frequencies. Experimental results of numerical simulations and listening tests using a practical system indicated that the perceptual quality of the sound field synthesized by the proposed method was improved from that synthesized by pressure matching.

NoisyILRMA: Diffuse-Noise-Aware Independent Low-Rank Matrix Analysis for Fast Blind Source Extraction

In this paper, we address the multichannel blind source extraction (BSE) of a single source in diffuse noise environments. To solve this problem even faster than by fast multichannel nonnegative matrix factorization (FastMNMF) and its variant, we propose a BSE method called NoisyILRMA, which is a modification of independent low-rank matrix analysis (ILRMA) to account for diffuse noise. NoisyILRMA can achieve considerably fast BSE by incorporating an algorithm developed for independent vector extraction. In addition, to improve the BSE performance of NoisyILRMA, we propose a mechanism to switch the source model with ILRMA-like nonnegative matrix factorization to a more expressive source model during optimization. In the experiment, we show that NoisyILRMA runs faster than a FastMNMF algorithm while maintaining the BSE performance. We also confirm that the switching mechanism improves the BSE performance of NoisyILRMA.

Algorithms of Sampling-Frequency-Independent Layers for Non-integer Strides

In this paper, we propose algorithms for handling non-integer strides in sampling-frequency-independent (SFI) convolutional and transposed convolutional layers. The SFI layers have been developed for handling various sampling frequencies (SFs) by a single neural network. They are replaceable with their non-SFI counterparts and can be introduced into various network architectures. However, they could not handle some specific configurations when combined with non-SFI layers. For example, an SFI extension of Conv-TasNet, a standard audio source separation model, cannot handle some pairs of trained and target SFs because the strides of the SFI layers become non-integers. This problem cannot be solved by simple rounding or signal resampling, resulting in the significant performance degradation. To overcome this problem, we propose algorithms for handling non-integer strides by using windowed sinc interpolation. The proposed algorithms realize the continuous-time representations of features using the interpolation and enable us to sample instants with the desired stride. Experimental results on music source separation showed that the proposed algorithms outperformed the rounding- and signal-resampling-based methods at SFs lower than the trained SF.

Multichannel Active Noise Control with Exterior Radiation Suppression Based on Riemannian Optimization

A multichannel active noise control (ANC) method with exterior radiation suppression is proposed. When applying ANC in a three-dimensional space by using multiple microphones and loudspeakers, the loudspeaker output can amplify noise outside a region of target positions because most of current ANC methods do not take into consideration the exterior radiation of secondary loudspeakers. We propose a normalized least mean square algorithm for feedforward ANC in the frequency domain based on the Riemannian optimization to update the control filter with the exterior radiation power constrained to a target value. The advantages of the proposed method, compared with the algorithm using a penalty term of exterior radiation, were validated by numerical experiments: the exterior radiation power can be constrained during the adaptation process and the parameter for the constraint can be determined in advance.

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.

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.

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.