arXiv subjects

Detai Xin

Publications and source records attributed to Detai Xin.

At least 19 recordsLinked to original sources

arXiv2026

PRISM-Bench: An Audio-Centric Diagnostic Benchmark for Text-to-Audio-Video Generation

Text-to-audio-video (T2AV) generation has advanced rapidly, but its evaluation still underestimates the audio modality. Existing benchmarks either treat audio as an auxiliary component of video quality or assess it in isolation from audiovisual grounding, making it difficult to diagnose where current systems truly succeed or fail in audio generation. We present PRISM-Bench, the first audio-centric diagnostic benchmark for T2AV generation. Built from a rigorously curated dataset of 900 human-verified samples, PRISM-Bench factorizes audio evaluation along two orthogonal axes: audio type (Speech, Music, and Sound) and sound-source visibility (On-screen vs. Off-screen). It evaluates generated content across four perceptual dimensions (Audio-Visual Coherence, Audio Quality, Audio Expressiveness, and Prompt Following) with 35 fine-grained criteria. To ensure reliable assessment, we adopt an enhanced MLLM-as-a-Judge protocol based on blind, side-by-side comparison against ground-truth references, demonstrating strong alignment (over 70% mean agreement) with human raters. Our evaluation of recent T2AV systems highlights a significant performance gap between frontier and open-source models. Furthermore, we demonstrate that current generation paradigms overfit to perceptual fidelity while struggling with complex grounding and control tasks, particularly in generating music and synchronized On-screen audio.

cs.MM↗

arXiv2026

LongCat-AudioDiT: High-Fidelity Diffusion Text-to-Speech in the Waveform Latent Space

We present LongCat-AudioDiT, a novel, non-autoregressive diffusion-based text-to-speech (TTS) model that achieves state-of-the-art (SOTA) performance. Unlike previous methods that rely on intermediate acoustic representations such as mel-spectrograms, the core innovation of LongCat-AudioDiT lies in operating directly within the waveform latent space. This approach effectively mitigates compounding errors and drastically simplifies the TTS pipeline, requiring only a waveform variational autoencoder (Wav-VAE) and a diffusion backbone. Furthermore, we introduce two critical improvements to the inference process: first, we identify and rectify a long-standing training-inference mismatch; second, we replace traditional classifier-free guidance with adaptive projection guidance to elevate generation quality. Experimental results demonstrate that, despite the absence of complex multi-stage training pipelines or high-quality human-annotated datasets, LongCat-AudioDiT achieves SOTA zero-shot voice cloning performance on the Seed benchmark while maintaining competitive intelligibility. Specifically, our largest variant, LongCat-AudioDiT-3.5B, outperforms the previous SOTA model (Seed-TTS), improving the speaker similarity (SIM) scores from 0.809 to 0.818 on Seed-ZH, and from 0.776 to 0.797 on Seed-Hard. Finally, through comprehensive ablation studies and systematic analysis, we validate the effectiveness of our proposed modules. Notably, we investigate the interplay between the Wav-VAE and the TTS backbone, revealing the counterintuitive finding that superior reconstruction fidelity in the Wav-VAE does not necessarily lead to better overall TTS performance. Code and model weights are released to foster further research within the speech community.

cs.SD↗

arXiv2025

LongCat-Flash-Omni Technical Report

We introduce LongCat-Flash-Omni, a state-of-the-art open-source omni-modal model with 560 billion parameters, excelling at real-time audio-visual interaction. By adopting a curriculum-inspired progressive training strategy that transitions from simpler to increasingly complex modality sequence modeling tasks, LongCat-Flash-Omni attains comprehensive multimodal capabilities while maintaining strong unimodal capability. Building upon LongCat-Flash, which adopts a high-performance Shortcut-connected Mixture-of-Experts (MoE) architecture with zero-computation experts, LongCat-Flash-Omni integrates efficient multimodal perception and speech reconstruction modules. Despite its immense size of 560B parameters (with 27B activated), LongCat-Flash-Omni achieves low-latency real-time audio-visual interaction. For training infrastructure, we developed a modality-decoupled parallelism scheme specifically designed to manage the data and model heterogeneity inherent in large-scale multimodal training. This innovative approach demonstrates exceptional efficiency by sustaining over 90% of the throughput achieved by text-only training. Extensive evaluations show that LongCat-Flash-Omni achieves state-of-the-art performance on omni-modal benchmarks among open-source models. Furthermore, it delivers highly competitive results across a wide range of modality-specific tasks, including text, image, and video understanding, as well as audio understanding and generation. We provide a comprehensive overview of the model architecture design, training procedures, and data strategies, and open-source the model to foster future research and development in the community.

cs.MM↗

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↗

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

RALL-E: Robust Codec Language Modeling with Chain-of-Thought Prompting for Text-to-Speech Synthesis

We present RALL-E, a robust language modeling method for text-to-speech (TTS) synthesis. While previous work based on large language models (LLMs) shows impressive performance on zero-shot TTS, such methods often suffer from poor robustness, such as unstable prosody (weird pitch and rhythm/duration) and a high word error rate (WER), due to the autoregressive prediction style of language models. The core idea behind RALL-E is chain-of-thought (CoT) prompting, which decomposes the task into simpler steps to enhance the robustness of LLM-based TTS. To accomplish this idea, RALL-E first predicts prosody features (pitch and duration) of the input text and uses them as intermediate conditions to predict speech tokens in a CoT style. Second, RALL-E utilizes the predicted duration prompt to guide the computing of self-attention weights in Transformer to enforce the model to focus on the corresponding phonemes and prosody features when predicting speech tokens. Results of comprehensive objective and subjective evaluations demonstrate that, compared to a powerful baseline method VALL-E, RALL-E significantly improves the WER of zero-shot TTS from $5.6\%$ (without reranking) and $1.7\%$ (with reranking) to $2.5\%$ and $1.0\%$, respectively. Furthermore, we demonstrate that RALL-E correctly synthesizes sentences that are hard for VALL-E and reduces the error rate from $68\%$ to $4\%$.

eess.AS↗

arXiv2024

NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models

While recent large-scale text-to-speech (TTS) models have achieved significant progress, they still fall short in speech quality, similarity, and prosody. Considering 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 NaturalSpeech 3, 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 to generate attributes in each subspace following its corresponding prompt. With this factorization design, NaturalSpeech 3 can effectively and efficiently model intricate speech with disentangled subspaces in a divide-and-conquer way. Experiments show that NaturalSpeech 3 outperforms the state-of-the-art TTS systems on quality, similarity, prosody, and intelligibility, and achieves on-par quality with human recordings. Furthermore, we achieve better performance by scaling to 1B parameters and 200K hours of training data.

eess.AS↗

arXiv2024

Building speech corpus with diverse voice characteristics for its prompt-based representation

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.

cs.SD↗

arXiv2023

JVNV: A Corpus of Japanese Emotional Speech with Verbal Content and Nonverbal Expressions

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.

cs.SD↗

arXiv2023

Coco-Nut: Corpus of Japanese Utterance and Voice Characteristics Description for Prompt-based Control

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.

cs.SD↗

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

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

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

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↗

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

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

UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022

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 fine-tuning 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.

cs.SD↗

arXiv2022

Exploring the Effectiveness of Self-supervised Learning and Classifier Chains in Emotion Recognition of Nonverbal Vocalizations

We present an emotion recognition system for nonverbal vocalizations (NVs) submitted to the ExVo Few-Shot track of the ICML Expressive Vocalizations Competition 2022. The proposed method uses self-supervised learning (SSL) models to extract features from NVs and uses a classifier chain to model the label dependency between emotions. Experimental results demonstrate that the proposed method can significantly improve the performance of this task compared to several baseline methods. Our proposed method obtained a mean concordance correlation coefficient (CCC) of $0.725$ in the validation set and $0.739$ in the test set, while the best baseline method only obtained $0.554$ in the validation set. We publicate our code at https://github.com/Aria-K-Alethia/ExVo to help others to reproduce our experimental results.

cs.SD↗