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. • Speaker-conditioned phrasing model improves accuracy in multi-speaker phrasing tasks. • We explore various speaker embeddings in phrasing models. • We apply phoneme-level pre-trained language models to enhance phrasing accuracy. • We propose a speaker adaptation method for few-shot phrasing tasks. • We verify that speaker embeddings learn human-aligned features via phrasing tasks.

While recent large-scale text-to-speech (TTS) models have achieved significant progress, they still fall shorts in speech quality, similarity, and prosody. Considering that speech intricately encompasses various attributes (e.g., content, prosody, timbre, and acoustic details) that pose significant challenges for generation, a natural idea is to factorize speech into individual subspaces representing different attributes and generate them individually. Motivated by it, we propose a TTS system with novel factorized diffusion models to generate natural speech in a zero-shot way. Specifically, 1) we design a neural codec with factorized vector quantization (FVQ) to disentangle speech waveform into subspaces of content, prosody, timbre, and acoustic details; 2) we propose a factorized diffusion model, which generates attributes in each subspace following its corresponding prompt. With this factorization design, our method can effectively and efficiently model the intricate speech with disentangled subspaces in a divide-and-conquer way. Experimental results show that our method outperforms the state-of-the-art TTS systems on quality, similarity, prosody, and intelligibility.

We present JNV (Japanese Nonverbal Vocalizations) corpus, a corpus of Japanese nonverbal vocalizations (NVs) with diverse phrases and emotions. Existing Japanese NV corpora either lack phrase diversity or focus on a small number of emotions, which makes it difficult to analyze the characteristics of Japanese 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 (1) the emotions of the collected NVs can be recognized with high accuracy by both human evaluators and statistical models; (2) the collected NVs have a high authenticity comparable to previous corpora of English NVs. Additionally, we analyze the distributions of vowel types in Japanese and conduct feature importance analysis to show discriminative acoustic features between emotion categories in Japanese NVs. We publicate JNV to advance further development in this field.

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.

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.

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.

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 embeddings 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.

We present the UTokyo-SaruLab mean opinion score (MOS) prediction system submitted to VoiceMOS Challenge 2022.The challenge is to predict the MOS values of speech samples collected from previous Blizzard Challenges and Voice Conversion Challenges for two tracks: a main track for in-domain prediction and an out-of-domain (OOD) track for which there is less labeled data from different listening tests.Our system is based on ensemble learning of strong and weak learners.Strong learners incorporate several improvements to the previous finetuning models of self-supervised learning (SSL) models, while weak learners use basic machine-learning methods to predict scores from SSL features.In the Challenge, our system had the highest score on several metrics for both the main and OOD tracks.In addition, we conducted ablation studies to investigate the effectiveness of our proposed methods.

We propose a method for obtaining disentangled speaker and language representations via mutual information minimization and domain adaptation for cross-lingual text-to-speech (TTS) synthesis. The proposed method extracts speaker and language embeddings from acoustic features by a speaker encoder and a language encoder. Then the proposed method applies domain adaptation on the two embeddings to obtain language-invariant speaker embedding and speaker-invariant language embedding. To get more disentangled representations, the proposed method further uses mutual information minimization between the two embeddings to remove entangled information within each embedding. Disentangled representations of speaker and language are critical for cross-lingual TTS synthesis since entangled representations make it difficult to maintain speaker identity information when changing the language representation and consequently causes performance degradation. We evaluate the proposed method using English and Japanese multi-speaker datasets with a total of 207 speakers. Experimental result demonstrates that the proposed method significantly improves the naturalness and speaker similarity of both intra-lingual and cross-lingual TTS synthesis. Furthermore, we show that the proposed method has a good capability of maintaining the speaker identity between languages.