Hongbin Zhou
Research Subjects
Hongbin Zhou has a total of 44 co-authors. Here are the top co-authors by number of shared publications:
- Jianhao Ye
Ximalaya Inc China
6 shared publications - Heng Lu
Ximalaya Inc., Shanghai, China
5 shared publications - Lei Xie
Speech and Language Processing Group (ASLP@NPU) Northwestern Polytechnical University Xi'an China
4 shared publications - Tianwei He
Ximalaya Inc
3 shared publications - Yuguang Yang
Ximalaya Inc ShangHai China
3 shared publications - Bin Lin
Ximalaya Inc China
2 shared publications
Latest Publications
- 26 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech and Language Processing
- Vol. 34, 557-566
FPO: Fine-Grained Preference Optimization Improves Zero-Shot Text-to-Speech
Integrating reinforcement learning to align generated speech with human preferences has proven effective in improving the robustness of language model-based text-to-speech (TTS) systems. Current approaches primarily rely on preference data annotated at the utterance level. However, frequent issues affecting the listening experience, such as unnatural prosody, mispronunciations, or semantic inconsistencies, often arise only in specific segments of audio, while other segments may be well-generated and require no correction. This mismatch between coarse-grained supervision and fine-grained quality variation limits the effectiveness of preference-based optimization. In this study, we propose a fine-grained preference optimization approach (FPO) to enhance the robustness of TTS systems. FPO shifts the optimization paradigm from global utterance-level tuning to targeted local refinement, focusing on addressing localized issues in generated samples rather than uniformly optimizing the entire utterance. We begin by analyzing the types of common generation issues and categorizing them into temporal modeling errors and semantic-phonetic alignment errors, which frequently degrade intelligibility and naturalness. To tackle these problems, we introduce a selective training loss strategy that leverages fine-grained labels for each issue type, allowing the model to focus on learning signals where they are most needed. Experimental results demonstrate that FPO substantially improves the robustness of zero-shot TTS systems by effectively correcting problematic regions in the output. This leads to a significant reduction in the bad case ratio, improved intelligibility, and overall perceptual quality. Moreover, FPO exhibits strong data efficiency, achieving comparable or superior performance to baseline methods while requiring notably fewer training samples. Audio samples can be found at https://yaoxunji.github.io/fpo/.
- 26 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech and Language Processing
- Vol. 34, 557-566
FPO: Fine-Grained Preference Optimization Improves Zero-Shot Text-to-Speech
Integrating reinforcement learning to align generated speech with human preferences has proven effective in improving the robustness of language model-based text-to-speech (TTS) systems. Current approaches primarily rely on preference data annotated at the utterance level. However, frequent issues affecting the listening experience, such as unnatural prosody, mispronunciations, or semantic inconsistencies, often arise only in specific segments of audio, while other segments may be well-generated and require no correction. This mismatch between coarse-grained supervision and fine-grained quality variation limits the effectiveness of preference-based optimization. In this study, we propose a fine-grained preference optimization approach (FPO) to enhance the robustness of TTS systems. FPO shifts the optimization paradigm from global utterance-level tuning to targeted local refinement, focusing on addressing localized issues in generated samples rather than uniformly optimizing the entire utterance. We begin by analyzing the types of common generation issues and categorizing them into temporal modeling errors and semantic-phonetic alignment errors, which frequently degrade intelligibility and naturalness. To tackle these problems, we introduce a selective training loss strategy that leverages fine-grained labels for each issue type, allowing the model to focus on learning signals where they are most needed. Experimental results demonstrate that FPO substantially improves the robustness of zero-shot TTS systems by effectively correcting problematic regions in the output. This leads to a significant reduction in the bad case ratio, improved intelligibility, and overall perceptual quality. Moreover, FPO exhibits strong data efficiency, achieving comparable or superior performance to baseline methods while requiring notably fewer training samples. Audio samples can be found at https://yaoxunji.github.io/fpo/.
- Open Access
Audiobook-CC: Controllable Long-context Speech Generation for Multicast Audiobook
Existing text-to-speech systems predominantly focus on single-sentence synthesis and lack adequate contextual modeling as well as fine-grained performance control capabilities for generating coherent multicast audiobooks. To address these limitations, we propose a context-aware and emotion controllable speech synthesis framework specifically engineered for multicast audiobooks with three key innovations: a context mechanism for contextual consistency, a disentanglement paradigm to decouple style control from speech prompts for semantic consistency, and self-distillation to boost emotional expressiveness and instruction controllability. Experimental results show superior performance across the generation of narration, dialogue, and the whole chapter, significantly outperforming existing baselines. Ablation studies are conducted to validate the effectiveness of our proposed methods. Demo samples can be found in https://everest-ai.github.io/.
Open AccessAudiobook-CC: Controllable Long-context Speech Generation for Multicast Audiobook
Existing text-to-speech systems predominantly focus on single-sentence synthesis and lack adequate contextual modeling as well as fine-grained performance control capabilities for generating coherent multicast audiobooks. To address these limitations, we propose a context-aware and emotion controllable speech synthesis framework specifically engineered for multicast audiobooks with three key innovations: a context mechanism for contextual consistency, a disentanglement paradigm to decouple style control from speech prompts for semantic consistency, and self-distillation to boost emotional expressiveness and instruction controllability. Experimental results show superior performance across the generation of narration, dialogue, and the whole chapter, significantly outperforming existing baselines. Ablation studies are conducted to validate the effectiveness of our proposed methods. Demo samples can be found in https://everest-ai.github.io/.
- Top Cited PapersOpen Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (24) , 25669-25677
StableVC: Style Controllable Zero-Shot Voice Conversion with Conditional Flow Matching
Zero-shot voice conversion (VC) aims to transfer the timbre from the source speaker to an arbitrary unseen speaker while preserving the original linguistic content. Despite recent advancements in zero-shot VC using language model-based or diffusion-based approaches, several challenges remain: 1) current approaches primarily focus on adapting timbre from unseen speakers and are unable to transfer style and timbre to different unseen speakers independently; 2) these approaches often suffer from slower inference speeds due to the autoregressive modeling methods or the need for numerous sampling steps; 3) the quality and similarity of the converted samples are still not fully satisfactory. To address these challenges, we propose a Style controllable zero-shot VC approach named StableVC, which aims to transfer timbre and style from source speech to different unseen target speakers. Specifically, we decompose speech into linguistic content, timbre, and style, and then employ a conditional flow matching module to reconstruct the high-quality mel-spectrogram based on these decomposed features. To effectively capture timbre and style in a zero-shot manner, we introduce a novel dual attention mechanism with an adaptive gate, rather than using conventional feature concatenation. With this non-autoregressive design, StableVC can efficiently capture the intricate timbre and style from different unseen speakers and generate high-quality speech significantly faster than real-time. Experiments demonstrate that our proposed StableVC outperforms state-of-the-art baseline systems in zero-shot VC and achieves flexible control over timbre and style from different unseen speakers. Moreover, StableVC offers approximately 25x and 1.65x faster sampling compared to autoregressive and diffusion-based baselines.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (24) , 25669-25677
Top Cited PapersOpen AccessStableVC: Style Controllable Zero-Shot Voice Conversion with Conditional Flow Matching
Zero-shot voice conversion (VC) aims to transfer the timbre from the source speaker to an arbitrary unseen speaker while preserving the original linguistic content. Despite recent advancements in zero-shot VC using language model-based or diffusion-based approaches, several challenges remain: 1) current approaches primarily focus on adapting timbre from unseen speakers and are unable to transfer style and timbre to different unseen speakers independently; 2) these approaches often suffer from slower inference speeds due to the autoregressive modeling methods or the need for numerous sampling steps; 3) the quality and similarity of the converted samples are still not fully satisfactory. To address these challenges, we propose a Style controllable zero-shot VC approach named StableVC, which aims to transfer timbre and style from source speech to different unseen target speakers. Specifically, we decompose speech into linguistic content, timbre, and style, and then employ a conditional flow matching module to reconstruct the high-quality mel-spectrogram based on these decomposed features. To effectively capture timbre and style in a zero-shot manner, we introduce a novel dual attention mechanism with an adaptive gate, rather than using conventional feature concatenation. With this non-autoregressive design, StableVC can efficiently capture the intricate timbre and style from different unseen speakers and generate high-quality speech significantly faster than real-time. Experiments demonstrate that our proposed StableVC outperforms state-of-the-art baseline systems in zero-shot VC and achieves flexible control over timbre and style from different unseen speakers. Moreover, StableVC offers approximately 25x and 1.65x faster sampling compared to autoregressive and diffusion-based baselines.
- Top Cited Papers
- 27 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech and Language Processing
- Vol. 33, 1243-1254
Vec-Tok Speech: Speech Vectorization and Tokenization for Neural Speech Generation
Language models (LMs) have recently flourished in natural language processing and computer vision, generating high-quality texts and images in various tasks. While current speech LMs have made significant progress, there are still challenges to overcome in terms of achieving optimal speech quality and broad task generalization. This paper presents Vec-Tok Speech, an extensible framework that resembles multiple speech generation tasks, generating expressive and high-fidelity speech. Specifically, we propose a novel speech codec based on speech vectors and semantic tokens. Speech vectors contain acoustic details contributing to high-fidelity speech reconstruction, while semantic tokens focus on the linguistic content of speech, facilitating language modeling. Based on the proposed speech codec, Vec-Tok Speech leverages an LM to undertake the core of speech generation. Moreover, Byte-Pair Encoding (BPE) is introduced to reduce the token length and bit rate for lower exposure bias and longer context, improving the performance of LMs. Vec-Tok Speech can be used for intra- and cross-lingual zero-shot voice conversion (VC), zero-shot speaking style transfer text-to-speech (TTS), speech-to-speech translation (S2ST), speech denoising, and speaker de-identification and anonymization. Experiments show that Vec-Tok Speech, built on 50,000 hours of speech, performs better than other SOTA models.
- 27 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech and Language Processing
- Vol. 33, 1243-1254
Top Cited PapersVec-Tok Speech: Speech Vectorization and Tokenization for Neural Speech Generation
Language models (LMs) have recently flourished in natural language processing and computer vision, generating high-quality texts and images in various tasks. While current speech LMs have made significant progress, there are still challenges to overcome in terms of achieving optimal speech quality and broad task generalization. This paper presents Vec-Tok Speech, an extensible framework that resembles multiple speech generation tasks, generating expressive and high-fidelity speech. Specifically, we propose a novel speech codec based on speech vectors and semantic tokens. Speech vectors contain acoustic details contributing to high-fidelity speech reconstruction, while semantic tokens focus on the linguistic content of speech, facilitating language modeling. Based on the proposed speech codec, Vec-Tok Speech leverages an LM to undertake the core of speech generation. Moreover, Byte-Pair Encoding (BPE) is introduced to reduce the token length and bit rate for lower exposure bias and longer context, improving the performance of LMs. Vec-Tok Speech can be used for intra- and cross-lingual zero-shot voice conversion (VC), zero-shot speaking style transfer text-to-speech (TTS), speech-to-speech translation (S2ST), speech denoising, and speaker de-identification and anonymization. Experiments show that Vec-Tok Speech, built on 50,000 hours of speech, performs better than other SOTA models.
- Open Access
StableVC: Style Controllable Zero-Shot Voice Conversion with Conditional Flow Matching
Zero-shot voice conversion (VC) aims to transfer the timbre from the source speaker to an arbitrary unseen speaker while preserving the original linguistic content. Despite recent advancements in zero-shot VC using language model-based or diffusion-based approaches, several challenges remain: 1) current approaches primarily focus on adapting timbre from unseen speakers and are unable to transfer style and timbre to different unseen speakers independently; 2) these approaches often suffer from slower inference speeds due to the autoregressive modeling methods or the need for numerous sampling steps; 3) the quality and similarity of the converted samples are still not fully satisfactory. To address these challenges, we propose a style controllable zero-shot VC approach named StableVC, which aims to transfer timbre and style from source speech to different unseen target speakers. Specifically, we decompose speech into linguistic content, timbre, and style, and then employ a conditional flow matching module to reconstruct the high-quality mel-spectrogram based on these decomposed features. To effectively capture timbre and style in a zero-shot manner, we introduce a novel dual attention mechanism with an adaptive gate, rather than using conventional feature concatenation. With this non-autoregressive design, StableVC can efficiently capture the intricate timbre and style from different unseen speakers and generate high-quality speech significantly faster than real-time. Experiments demonstrate that our proposed StableVC outperforms state-of-the-art baseline systems in zero-shot VC and achieves flexible control over timbre and style from different unseen speakers. Moreover, StableVC offers approximately 25x and 1.65x faster sampling compared to autoregressive and diffusion-based baselines.
Open AccessStableVC: Style Controllable Zero-Shot Voice Conversion with Conditional Flow Matching
Zero-shot voice conversion (VC) aims to transfer the timbre from the source speaker to an arbitrary unseen speaker while preserving the original linguistic content. Despite recent advancements in zero-shot VC using language model-based or diffusion-based approaches, several challenges remain: 1) current approaches primarily focus on adapting timbre from unseen speakers and are unable to transfer style and timbre to different unseen speakers independently; 2) these approaches often suffer from slower inference speeds due to the autoregressive modeling methods or the need for numerous sampling steps; 3) the quality and similarity of the converted samples are still not fully satisfactory. To address these challenges, we propose a style controllable zero-shot VC approach named StableVC, which aims to transfer timbre and style from source speech to different unseen target speakers. Specifically, we decompose speech into linguistic content, timbre, and style, and then employ a conditional flow matching module to reconstruct the high-quality mel-spectrogram based on these decomposed features. To effectively capture timbre and style in a zero-shot manner, we introduce a novel dual attention mechanism with an adaptive gate, rather than using conventional feature concatenation. With this non-autoregressive design, StableVC can efficiently capture the intricate timbre and style from different unseen speakers and generate high-quality speech significantly faster than real-time. Experiments demonstrate that our proposed StableVC outperforms state-of-the-art baseline systems in zero-shot VC and achieves flexible control over timbre and style from different unseen speakers. Moreover, StableVC offers approximately 25x and 1.65x faster sampling compared to autoregressive and diffusion-based baselines.
- Open Access
Takin-ADA: Emotion Controllable Audio-Driven Animation with Canonical and Landmark Loss Optimization
Existing audio-driven facial animation methods face critical challenges, including expression leakage, ineffective subtle expression transfer, and imprecise audio-driven synchronization. We discovered that these issues stem from limitations in motion representation and the lack of fine-grained control over facial expressions. To address these problems, we present Takin-ADA, a novel two-stage approach for real-time audio-driven portrait animation. In the first stage, we introduce a specialized loss function that enhances subtle expression transfer while reducing unwanted expression leakage. The second stage utilizes an advanced audio processing technique to improve lip-sync accuracy. Our method not only generates precise lip movements but also allows flexible control over facial expressions and head motions. Takin-ADA achieves high-resolution (512x512) facial animations at up to 42 FPS on an RTX 4090 GPU, outperforming existing commercial solutions. Extensive experiments demonstrate that our model significantly surpasses previous methods in video quality, facial dynamics realism, and natural head movements, setting a new benchmark in the field of audio-driven facial animation.
Open AccessTakin-ADA: Emotion Controllable Audio-Driven Animation with Canonical and Landmark Loss Optimization
Existing audio-driven facial animation methods face critical challenges, including expression leakage, ineffective subtle expression transfer, and imprecise audio-driven synchronization. We discovered that these issues stem from limitations in motion representation and the lack of fine-grained control over facial expressions. To address these problems, we present Takin-ADA, a novel two-stage approach for real-time audio-driven portrait animation. In the first stage, we introduce a specialized loss function that enhances subtle expression transfer while reducing unwanted expression leakage. The second stage utilizes an advanced audio processing technique to improve lip-sync accuracy. Our method not only generates precise lip movements but also allows flexible control over facial expressions and head motions. Takin-ADA achieves high-resolution (512x512) facial animations at up to 42 FPS on an RTX 4090 GPU, outperforming existing commercial solutions. Extensive experiments demonstrate that our model significantly surpasses previous methods in video quality, facial dynamics realism, and natural head movements, setting a new benchmark in the field of audio-driven facial animation.
- 7 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 32 (23299290) , 1506-1518
METTS: Multilingual Emotional Text-to-Speech by Cross-Speaker and Cross-Lingual Emotion Transfer
Previous multilingual text-to-speech (TTS) approaches have considered leveraging monolingual speaker data to enable cross-lingual speech synthesis. However, such data-efficient approaches have ignored synthesizing emotional aspects of speech due to the challenges of cross-speaker cross-lingual emotion transfer – the heavy entanglement of speaker timbre , emotion and language factors in the speech signal will make a system to produce cross-lingual synthetic speech with an undesired foreign accent and weak emotion expressiveness. This paper proposes a Multilingual Emotional TTS (METTS) model to mitigate these problems, realizing both cross-speaker and cross-lingual emotion transfer. Specifically, METTS takes DelightfulTTS as the backbone model and proposes the following designs. First, to alleviate the foreign accent problem, METTS introduces multi-scale emotion modeling to disentangle speech prosody into coarse-grained and fine-grained scales, producing language-agnostic and language-specific emotion representations, respectively. Second, as a pre-processing step, formant shift based information perturbation is applied to the reference signal for better disentanglement of speaker timbre in the speech. Third, a vector quantization based emotion matcher is designed for reference selection, leading to decent naturalness and emotion diversity in cross-lingual synthetic speech. Experiments demonstrate the good design of METTS.
- 7 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 32 (23299290) , 1506-1518
METTS: Multilingual Emotional Text-to-Speech by Cross-Speaker and Cross-Lingual Emotion Transfer
Previous multilingual text-to-speech (TTS) approaches have considered leveraging monolingual speaker data to enable cross-lingual speech synthesis. However, such data-efficient approaches have ignored synthesizing emotional aspects of speech due to the challenges of cross-speaker cross-lingual emotion transfer – the heavy entanglement of speaker timbre , emotion and language factors in the speech signal will make a system to produce cross-lingual synthetic speech with an undesired foreign accent and weak emotion expressiveness. This paper proposes a Multilingual Emotional TTS (METTS) model to mitigate these problems, realizing both cross-speaker and cross-lingual emotion transfer. Specifically, METTS takes DelightfulTTS as the backbone model and proposes the following designs. First, to alleviate the foreign accent problem, METTS introduces multi-scale emotion modeling to disentangle speech prosody into coarse-grained and fine-grained scales, producing language-agnostic and language-specific emotion representations, respectively. Second, as a pre-processing step, formant shift based information perturbation is applied to the reference signal for better disentanglement of speaker timbre in the speech. Third, a vector quantization based emotion matcher is designed for reference selection, leading to decent naturalness and emotion diversity in cross-lingual synthetic speech. Experiments demonstrate the good design of METTS.
- Open Access
METTS: Multilingual Emotional Text-to-Speech by Cross-speaker and Cross-lingual Emotion Transfer
Previous multilingual text-to-speech (TTS) approaches have considered leveraging monolingual speaker data to enable cross-lingual speech synthesis. However, such data-efficient approaches have ignored synthesizing emotional aspects of speech due to the challenges of cross-speaker cross-lingual emotion transfer - the heavy entanglement of speaker timbre, emotion, and language factors in the speech signal will make a system produce cross-lingual synthetic speech with an undesired foreign accent and weak emotion expressiveness. This paper proposes the Multilingual Emotional TTS (METTS) model to mitigate these problems, realizing both cross-speaker and cross-lingual emotion transfer. Specifically, METTS takes DelightfulTTS as the backbone model and proposes the following designs. First, to alleviate the foreign accent problem, METTS introduces multi-scale emotion modeling to disentangle speech prosody into coarse-grained and fine-grained scales, producing language-agnostic and language-specific emotion representations, respectively. Second, as a pre-processing step, formant shift-based information perturbation is applied to the reference signal for better disentanglement of speaker timbre in the speech. Third, a vector quantization-based emotion matcher is designed for reference selection, leading to decent naturalness and emotion diversity in cross-lingual synthetic speech. Experiments demonstrate the good design of METTS.
Open AccessMETTS: Multilingual Emotional Text-to-Speech by Cross-speaker and Cross-lingual Emotion Transfer
Previous multilingual text-to-speech (TTS) approaches have considered leveraging monolingual speaker data to enable cross-lingual speech synthesis. However, such data-efficient approaches have ignored synthesizing emotional aspects of speech due to the challenges of cross-speaker cross-lingual emotion transfer - the heavy entanglement of speaker timbre, emotion, and language factors in the speech signal will make a system produce cross-lingual synthetic speech with an undesired foreign accent and weak emotion expressiveness. This paper proposes the Multilingual Emotional TTS (METTS) model to mitigate these problems, realizing both cross-speaker and cross-lingual emotion transfer. Specifically, METTS takes DelightfulTTS as the backbone model and proposes the following designs. First, to alleviate the foreign accent problem, METTS introduces multi-scale emotion modeling to disentangle speech prosody into coarse-grained and fine-grained scales, producing language-agnostic and language-specific emotion representations, respectively. Second, as a pre-processing step, formant shift-based information perturbation is applied to the reference signal for better disentanglement of speaker timbre in the speech. Third, a vector quantization-based emotion matcher is designed for reference selection, leading to decent naturalness and emotion diversity in cross-lingual synthetic speech. Experiments demonstrate the good design of METTS.
- 10 May 2023
- Published by Springer Nature
- p. 306-317
Automatic Stress Annotation and Prediction for Expressive Mandarin TTS
- 10 May 2023
- Published by Springer Nature
- p. 306-317
Automatic Stress Annotation and Prediction for Expressive Mandarin TTS
- 10 May 2023
- Published by Springer Nature
- p. 196-207
Improving Fine-Grained Emotion Control and Transfer with Gated Emotion Representations in Speech Synthesis
- 10 May 2023
- Published by Springer Nature
- p. 196-207
Improving Fine-Grained Emotion Control and Transfer with Gated Emotion Representations in Speech Synthesis