ZhenHua Ling

Pengyu Cheng, Zhenhua Ling

In this paper, we propose a method of speaker adaption with intuitive prosodic features for statistical parametric speech synthesis. The intuitive prosodic features employed in this method include pitch, pitch range, speech rate and energy considering that they are directly related with the overall prosodic characteristics of different speakers. The intuitive prosodic features are extracted at utterance-level or speaker-level, and are further integrated into the existing speaker-encoding-based and speaker-embedding-based adaptation frameworks respectively. The acoustic models are sequence-to-sequence ones based on Tacotron2. Intuitive prosodic features are concatenated with text encoder outputs and speaker vectors for decoding acoustic features.Experimental results have demonstrated that our proposed methods can achieve better objective and subjective performance than the baseline methods without intuitive prosodic features. Besides, the proposed speaker adaption method with utterance-level prosodic features has achieved the best similarity of synthetic speech among all compared methods.

Lu Dong, Zhenhua Ling, Qiang Ling et al.

Cognitive diagnosis is an essential task in many educational applications. Many solutions have been designed in the literature. The deterministic input, noisy "and" gate (DINA) model is a classical cognitive diagnosis model and can provide interpretable cognitive parameters, e.g., student vectors. However, the assumption of the probabilistic part of DINA is too strong, because it assumes that the slip and guess rates of questions are student-independent. Besides, the question matrix (i.e., Q-matrix) recording the skill distribution of the questions in the cognitive diagnosis domain often requires precise labels given by domain experts. Thus, we propose an explicit student vector estimation (ESVE) method to estimate the student vectors of DINA with a local self-consistent test, which does not rely on any assumptions for the probabilistic part of DINA. Then, based on the estimated student vectors, the probabilistic part of DINA can be modified to a student dependent model that the slip and guess rates are related to student vectors. Furthermore, we propose an unsupervised method called heuristic bidirectional calibration algorithm (HBCA) to label the Q-matrix automatically, which connects the question difficulty relation and the answer results for initialization and uses the fault tolerance of ESVE-DINA for calibration. The experimental results on two real-world datasets show that ESVE-DINA outperforms the DINA model on accuracy and that the Q-matrix labeled automatically by HBCA can achieve performance comparable to that obtained with the manually labeled Q-matrix when using the same model structure.

Jiaxuan Liu, Yang Xiang, Han Zhao et al.

Movie dubbing is the task of synthesizing speech from scripts conditioned on video scenes, requiring accurate lip sync, faithful timbre transfer, and proper modeling of character identity and emotion. However, existing methods face two major limitations: (1) high-quality multimodal dubbing datasets are limited in scale, suffer from high word error rates, contain sparse annotations, rely on costly manual labeling, and are restricted to monologue scenes, all of which hinder effective model training; (2) existing dubbing models rely solely on the lip region to learn audio-visual alignment, which limits their applicability to complex live-action cinematic scenes, and exhibit suboptimal performance in lip sync, speech quality, and emotional expressiveness. To address these issues, we propose FunCineForge, which comprises an end-to-end production pipeline for large-scale dubbing datasets and an MLLM-based dubbing model designed for diverse cinematic scenes. Using the pipeline, we construct the first Chinese television dubbing dataset with rich annotations, and demonstrate the high quality of these data. Experiments across monologue, narration, dialogue, and multi-speaker scenes show that our dubbing model consistently outperforms SOTA methods in audio quality, lip sync, timbre transfer, and instruction following. Code and demos are available at https://anonymous.4open.science/w/FunCineForge.

Rusheng Pan, Bingcheng Mao, Tianyi Ma et al.

Recovering accurate architecture from large-scale legacy software is hindered by architectural drift, missing relations, and the limited context of Large Language Models (LLMs). We present ArchAgent, a scalable agent-based framework that combines static analysis, adaptive code segmentation, and LLM-powered synthesis to reconstruct multiview, business-aligned architectures from cross-repository codebases. ArchAgent introduces scalable diagram generation with contextual pruning and integrates cross-repository data to identify business-critical modules. Evaluations of typical large-scale GitHub projects show significant improvements over existing benchmarks. An ablation study confirms that dependency context improves the accuracy of generated architectures of production-level repositories, and a real-world case study demonstrates effective recovery of critical business logics from legacy projects. The dataset is available at https://github.com/panrusheng/arch-eval-benchmark.

Beiduo Chen, Shaohan Huang, Zihan Zhang et al.

ELECTRA, the generator-discriminator pre-training framework, has achieved impressive semantic construction capability among various downstream tasks. Despite the convincing performance, ELECTRA still faces the challenges of monotonous training and deficient interaction. Generator with only masked language modeling (MLM) leads to biased learning and label imbalance for discriminator, decreasing learning efficiency; no explicit feedback loop from discriminator to generator results in the chasm between these two components, underutilizing the course learning. In this study, a multi-perspective course learning (MCL) method is proposed to fetch a many degrees and visual angles for sample-efficient pre-training, and to fully leverage the relationship between generator and discriminator. Concretely, three self-supervision courses are designed to alleviate inherent flaws of MLM and balance the label in a multi-perspective way. Besides, two self-correction courses are proposed to bridge the chasm between the two encoders by creating a "correction notebook" for secondary-supervision. Moreover, a course soups trial is conducted to solve the "tug-of-war" dynamics problem of MCL, evolving a stronger pre-trained model. Experimental results show that our method significantly improves ELECTRA's average performance by 2.8% and 3.2% absolute points respectively on GLUE and SQuAD 2.0 benchmarks, and overshadows recent advanced ELECTRA-style models under the same settings. The pre-trained MCL model is available at https://huggingface.co/McmanusChen/MCL-base.

Boyuan Zheng, Xiaoyu Yang, Yu-Ping Ruan et al.

This paper introduces the SemEval-2021 shared task 4: Reading Comprehension of Abstract Meaning (ReCAM). This shared task is designed to help evaluate the ability of machines in representing and understanding abstract concepts. Given a passage and the corresponding question, a participating system is expected to choose the correct answer from five candidates of abstract concepts in a cloze-style machine reading comprehension setup. Based on two typical definitions of abstractness, i.e., the imperceptibility and nonspecificity, our task provides three subtasks to evaluate the participating models. Specifically, Subtask 1 aims to evaluate how well a system can model concepts that cannot be directly perceived in the physical world. Subtask 2 focuses on models' ability in comprehending nonspecific concepts located high in a hypernym hierarchy given the context of a passage. Subtask 3 aims to provide some insights into models' generalizability over the two types of abstractness. During the SemEval-2021 official evaluation period, we received 23 submissions to Subtask 1 and 28 to Subtask 2. The participating teams additionally made 29 submissions to Subtask 3. The leaderboard and competition website can be found at https://competitions.codalab.org/competitions/26153. The data and baseline code are available at https://github.com/boyuanzheng010/SemEval2021-Reading-Comprehension-of-Abstract-Meaning.

Zhengyan Sheng, Zhihao Du, Shiliang Zhang et al.

This paper presents a dual-stream text-to-speech (TTS) model, SyncSpeech, capable of receiving streaming text input from upstream models while simultaneously generating streaming speech, facilitating seamless interaction with large language models. SyncSpeech has the following advantages: Low latency, as it begins generating streaming speech upon receiving the second text token; High efficiency, as it decodes all speech tokens corresponding to the each arrived text token in one step. To achieve this, we propose a temporal masked transformer as the backbone of SyncSpeech, combined with token-level duration prediction to predict speech tokens and the duration for the next step. Additionally, we design a two-stage training strategy to improve training efficiency and the quality of generated speech. We evaluated the SyncSpeech on both English and Mandarin datasets. Compared to the recent dual-stream TTS models, SyncSpeech significantly reduces the first packet delay of speech tokens and accelerates the real-time factor. Moreover, with the same data scale, SyncSpeech achieves performance comparable to that of traditional autoregressive-based TTS models in terms of both speech quality and robustness. Speech samples are available at https://SyncSpeech.github.io/}{https://SyncSpeech.github.io/.

Jiaxuan Liu, Zhaoci Liu, Yajun Hu et al.

Human speech exhibits rich and flexible prosodic variations. To address the one-to-many mapping problem from text to prosody in a reasonable and flexible manner, we propose DiffStyleTTS, a multi-speaker acoustic model based on a conditional diffusion module and an improved classifier-free guidance, which hierarchically models speech prosodic features, and controls different prosodic styles to guide prosody prediction. Experiments show that our method outperforms all baselines in naturalness and achieves superior synthesis speed compared to three diffusion-based baselines. Additionally, by adjusting the guiding scale, DiffStyleTTS effectively controls the guidance intensity of the synthetic prosody.

Bolei He, Xinran He, Run Shao et al.

Large Language Models (LLMs) perform well in general QA but often struggle in domain-specific scenarios. Retrieval-Augmented Generation (RAG) introduces external knowledge but suffers from hallucinations and latency due to noisy retrievals. Continued pretraining internalizes domain knowledge but is costly and lacks cross-domain flexibility. We attribute this challenge to the long-tail distribution of domain knowledge, which leaves partial yet useful internal knowledge underutilized. We further argue that knowledge acquisition should be progressive, mirroring human learning: first understanding concepts, then applying them to complex reasoning. To address this, we propose Selct2Know (S2K), a cost-effective framework that internalizes domain knowledge through an internal-external knowledge self-selection strategy and selective supervised fine-tuning. We also introduce a structured reasoning data generation pipeline and integrate GRPO to enhance reasoning ability. Experiments on medical, legal, and financial QA benchmarks show that S2K consistently outperforms existing methods and matches domain-pretrained LLMs with significantly lower cost.

Bolei He, Xinran He, Mengke Chen et al.

Large Language Models (LLMs) excel in many areas but continue to face challenges with complex reasoning tasks, such as Multi-Hop Question Answering (MHQA). MHQA requires integrating evidence from diverse sources while managing intricate logical dependencies, often leads to errors in reasoning. Retrieval-Augmented Generation (RAG), widely employed in MHQA tasks, faces challenges in effectively filtering noisy data and retrieving all necessary evidence, thereby limiting its effectiveness in addressing MHQA challenges. To address these challenges, we propose RISE:Reasoning Enhancement via Iterative Self-Exploration, a novel framework designed to enhance models' reasoning capability through iterative self-exploration. Specifically, RISE involves three key steps in addressing MHQA tasks: question decomposition, retrieve-then-read, and self-critique. By leveraging continuous self-exploration, RISE identifies accurate reasoning paths, iteratively self-improving the model's capability to integrate evidence, maintain logical consistency, and enhance performance in MHQA tasks. Extensive experiments on multiple MHQA benchmarks demonstrate that RISE significantly improves reasoning accuracy and task performance.

ShiMing Wang, ZhiHao Du, Yang Xiang et al.

This paper focuses on resolving stability hallucinations (e.g., repetitive or omitted speech) in LLM-based Text-to-Speech (TTS) models by improving and leveraging the attention mechanism. First, we analyzed the alignment mechanism between text tokens and speech tokens in LLMs. We then proposed a metric termed the Optimal Alignment Score (OAS), which employs the Viterbi algorithm to evaluate text-speech alignment quality. Subsequently, OAS was integrated into the training of CosyVoice2 to assist LLMs in learning continuous, stable alignment. Additionally, the pre-trained attention value is employed to guide the training of the student CosyVoice2 via chain-of-thought (CoT), which further reduces stability hallucinations in synthesized speech. Experiments on the Seed-TTS-Eval and CV3-Eval test sets demonstrate that the proposed methods can effectively reduce the stability hallucinations of CosyVoice2 without introducing additional negative effects. The appendix is available at https://wsmzzz.github.io/llm_attn.

Jiaxuan Liu, Yang Xiang, Han Zhao et al.

Recent large language models (LLMs) have made great progress in the field of text-to-speech (TTS), but they still face major challenges in synthesizing fine-grained emotional speech in an interpretable manner. Traditional methods rely on discrete emotion labels to control emotion categories and intensities, which cannot capture the complexity and continuity of human emotional perception and expression. The lack of large-scale emotional speech datasets with balanced emotion distributions and fine-grained emotional annotations often causes overfitting in synthesis models and impedes effective emotion control. To address these issues, we propose UDDETTS, a universal LLM framework unifying discrete and dimensional emotions for controllable emotional TTS. This model introduces the interpretable Arousal-Dominance-Valence (ADV) space for dimensional emotion description and supports emotion control driven by either discrete emotion labels or nonlinearly quantified ADV values. Furthermore, a semi-supervised training strategy is designed to comprehensively utilize diverse speech datasets with different types of emotional annotations to train the UDDETTS. Experiments show that UDDETTS achieves linear emotion control along three interpretable dimensions, and exhibits superior end-to-end emotional speech synthesis capabilities. Code and demos are available at: https://anonymous.4open.science/w/UDDETTS.

Cheng Gong, Longbiao Wang, Zhenhua Ling et al.

The end-to-end speech synthesis model can directly take an utterance as reference audio, and generate speech from the text with prosody and speaker characteristics similar to the reference audio. However, an appropriate acoustic embedding must be manually selected during inference. Due to the fact that only the matched text and speech are used in the training process, using unmatched text and speech for inference would cause the model to synthesize speech with low content quality. In this study, we propose to mitigate these two problems by using multiple reference audios and style embedding constraints rather than using only the target audio. Multiple reference audios are automatically selected using the sentence similarity determined by Bidirectional Encoder Representations from Transformers (BERT). In addition, we use ''target'' style embedding from a Pre-trained encoder as a constraint by considering the mutual information between the predicted and ''target'' style embedding. The experimental results show that the proposed model can improve the speech naturalness and content quality with multiple reference audios and can also outperform the baseline model in ABX preference tests of style similarity.

Yang Ai, Haoyu Li, Xin Wang et al.

This paper presents a denoising and dereverberation hierarchical neural vocoder (DNR-HiNet) to convert noisy and reverberant acoustic features into a clean speech waveform. We implement it mainly by modifying the amplitude spectrum predictor (ASP) in the original HiNet vocoder. This modified denoising and dereverberation ASP (DNR-ASP) can predict clean log amplitude spectra (LAS) from input degraded acoustic features. To achieve this, the DNR-ASP first predicts the noisy and reverberant LAS, noise LAS related to the noise information, and room impulse response related to the reverberation information then performs initial denoising and dereverberation. The initial processed LAS are then enhanced by another neural network as the final clean LAS. To further improve the quality of the generated clean LAS, we also introduce a bandwidth extension model and frequency resolution extension model in the DNR-ASP. The experimental results indicate that the DNR-HiNet vocoder was able to generate a denoised and dereverberated waveform given noisy and reverberant acoustic features and outperformed the original HiNet vocoder and a few other neural vocoders. We also applied the DNR-HiNet vocoder to speech enhancement tasks, and its performance was competitive with several advanced speech enhancement methods.

Rohan Kumar Das, Tomi Kinnunen, Wen-Chin Huang et al.

The Voice Conversion Challenge 2020 is the third edition under its flagship that promotes intra-lingual semiparallel and cross-lingual voice conversion (VC). While the primary evaluation of the challenge submissions was done through crowd-sourced listening tests, we also performed an objective assessment of the submitted systems. The aim of the objective assessment is to provide complementary performance analysis that may be more beneficial than the time-consuming listening tests. In this study, we examined five types of objective assessments using automatic speaker verification (ASV), neural speaker embeddings, spoofing countermeasures, predicted mean opinion scores (MOS), and automatic speech recognition (ASR). Each of these objective measures assesses the VC output along different aspects. We observed that the correlations of these objective assessments with the subjective results were high for ASV, neural speaker embedding, and ASR, which makes them more influential for predicting subjective test results. In addition, we performed spoofing assessments on the submitted systems and identified some of the VC methods showing a potentially high security risk.

Yi Zhao, Wen-Chin Huang, Xiaohai Tian et al.

The voice conversion challenge is a bi-annual scientific event held to compare and understand different voice conversion (VC) systems built on a common dataset. In 2020, we organized the third edition of the challenge and constructed and distributed a new database for two tasks, intra-lingual semi-parallel and cross-lingual VC. After a two-month challenge period, we received 33 submissions, including 3 baselines built on the database. From the results of crowd-sourced listening tests, we observed that VC methods have progressed rapidly thanks to advanced deep learning methods. In particular, speaker similarity scores of several systems turned out to be as high as target speakers in the intra-lingual semi-parallel VC task. However, we confirmed that none of them have achieved human-level naturalness yet for the same task. The cross-lingual conversion task is, as expected, a more difficult task, and the overall naturalness and similarity scores were lower than those for the intra-lingual conversion task. However, we observed encouraging results, and the MOS scores of the best systems were higher than 4.0. We also show a few additional analysis results to aid in understanding cross-lingual VC better.

Tomi Kinnunen, Jaime Lorenzo-Trueba, Junichi Yamagishi et al.

Voice conversion (VC) aims at conversion of speaker characteristic without altering content. Due to training data limitations and modeling imperfections, it is difficult to achieve believable speaker mimicry without introducing processing artifacts; performance assessment of VC, therefore, usually involves both speaker similarity and quality evaluation by a human panel. As a time-consuming, expensive, and non-reproducible process, it hinders rapid prototyping of new VC technology. We address artifact assessment using an alternative, objective approach leveraging from prior work on spoofing countermeasures (CMs) for automatic speaker verification. Therein, CMs are used for rejecting `fake' inputs such as replayed, synthetic or converted speech but their potential for automatic speech artifact assessment remains unknown. This study serves to fill that gap. As a supplement to subjective results for the 2018 Voice Conversion Challenge (VCC'18) data, we configure a standard constant-Q cepstral coefficient CM to quantify the extent of processing artifacts. Equal error rate (EER) of the CM, a confusability index of VC samples with real human speech, serves as our artifact measure. Two clusters of VCC'18 entries are identified: low-quality ones with detectable artifacts (low EERs), and higher quality ones with less artifacts. None of the VCC'18 systems, however, is perfect: all EERs are < 30 % (the `ideal' value would be 50 %). Our preliminary findings suggest potential of CMs outside of their original application, as a supplemental optimization and benchmarking tool to enhance VC technology.

Jaime Lorenzo-Trueba, Junichi Yamagishi, Tomoki Toda et al.

We present the Voice Conversion Challenge 2018, designed as a follow up to the 2016 edition with the aim of providing a common framework for evaluating and comparing different state-of-the-art voice conversion (VC) systems. The objective of the challenge was to perform speaker conversion (i.e. transform the vocal identity) of a source speaker to a target speaker while maintaining linguistic information. As an update to the previous challenge, we considered both parallel and non-parallel data to form the Hub and Spoke tasks, respectively. A total of 23 teams from around the world submitted their systems, 11 of them additionally participated in the optional Spoke task. A large-scale crowdsourced perceptual evaluation was then carried out to rate the submitted converted speech in terms of naturalness and similarity to the target speaker identity. In this paper, we present a brief summary of the state-of-the-art techniques for VC, followed by a detailed explanation of the challenge tasks and the results that were obtained.

Qian Chen, Xiaodan Zhu, Zhenhua Ling et al.

Distributed representation learned with neural networks has recently shown to be effective in modeling natural languages at fine granularities such as words, phrases, and even sentences. Whether and how such an approach can be extended to help model larger spans of text, e.g., documents, is intriguing, and further investigation would still be desirable. This paper aims to enhance neural network models for such a purpose. A typical problem of document-level modeling is automatic summarization, which aims to model documents in order to generate summaries. In this paper, we propose neural models to train computers not just to pay attention to specific regions and content of input documents with attention models, but also distract them to traverse between different content of a document so as to better grasp the overall meaning for summarization. Without engineering any features, we train the models on two large datasets. The models achieve the state-of-the-art performance, and they significantly benefit from the distraction modeling, particularly when input documents are long.

Qian Chen, Xiaodan Zhu, Zhenhua Ling et al.

Reasoning and inference are central to human and artificial intelligence. Modeling inference in human language is very challenging. With the availability of large annotated data (Bowman et al., 2015), it has recently become feasible to train neural network based inference models, which have shown to be very effective. In this paper, we present a new state-of-the-art result, achieving the accuracy of 88.6% on the Stanford Natural Language Inference Dataset. Unlike the previous top models that use very complicated network architectures, we first demonstrate that carefully designing sequential inference models based on chain LSTMs can outperform all previous models. Based on this, we further show that by explicitly considering recursive architectures in both local inference modeling and inference composition, we achieve additional improvement. Particularly, incorporating syntactic parsing information contributes to our best result---it further improves the performance even when added to the already very strong model.