Jingbei Li

Yong Ren, Jingbei Li, Haiyang Sun et al.

Recent advances in Large Audio Language Models (LALMs) have extended Text-to-Speech (TTS) to interactive role-play scenarios, which demand high expressiveness and strict adherence to role-play instructions. However, existing models struggle to maintain stylistic consistency with character profiles and scene descriptions across multi-turn dialogues. A critical bottleneck is the lack of objective metrics for quantifying speaking style. To bridge this gap, we propose Mean Continuation Log-Probability (MCLP) as both an evaluation metric and a reward signal, validated on LALM-based Role-Play TTS (RP-TTS) tasks. MCLP leverages the in-context learning capability of pretrained LALMs to measure the likelihood of ground-truth speech tokens conditioned on a contextual history consisting of the transcript, generated speech, and repeated transcript, serving as a proxy for stylistic continuity. Furthermore, we employ MCLP as a reinforcement learning reward to enhance the style alignment between generated speech and role-play instructions. To support this task, we construct a large-scale RP-TTS dataset with rich scene and character annotations. Experiments demonstrate that MCLP is well aligned with human judgments of stylistic consistency and serves as an effective reward for improving RP-TTS, leading to consistent gains in both objective metrics and subjective evaluations. Our code is publicly available at https://github.com/y-ren16/MCLP.

Ailin Huang, Boyong Wu, Bruce Wang et al.

Real-time speech interaction, serving as a fundamental interface for human-machine collaboration, holds immense potential. However, current open-source models face limitations such as high costs in voice data collection, weakness in dynamic control, and limited intelligence. To address these challenges, this paper introduces Step-Audio, the first production-ready open-source solution. Key contributions include: 1) a 130B-parameter unified speech-text multi-modal model that achieves unified understanding and generation, with the Step-Audio-Chat version open-sourced; 2) a generative speech data engine that establishes an affordable voice cloning framework and produces the open-sourced lightweight Step-Audio-TTS-3B model through distillation; 3) an instruction-driven fine control system enabling dynamic adjustments across dialects, emotions, singing, and RAP; 4) an enhanced cognitive architecture augmented with tool calling and role-playing abilities to manage complex tasks effectively. Based on our new StepEval-Audio-360 evaluation benchmark, Step-Audio achieves state-of-the-art performance in human evaluations, especially in terms of instruction following. On open-source benchmarks like LLaMA Question, shows 9.3% average performance improvement, demonstrating our commitment to advancing the development of open-source multi-modal language technologies. Our code and models are available at https://github.com/stepfun-ai/Step-Audio.

Boyong Wu, Chao Yan, Chen Hu et al.

This paper presents Step-Audio 2, an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation. By integrating a latent audio encoder and reasoning-centric reinforcement learning (RL), Step-Audio 2 achieves promising performance in automatic speech recognition (ASR) and audio understanding. To facilitate genuine end-to-end speech conversation, Step-Audio 2 incorporates the generation of discrete audio tokens into language modeling, significantly enhancing its responsiveness to paralinguistic information such as speaking styles and emotions. To effectively leverage the rich textual and acoustic knowledge in real-world data, Step-Audio 2 integrates retrieval-augmented generation (RAG) and is able to call external tools such as web search to mitigate hallucination and audio search to switch timbres. Trained on millions of hours of speech and audio data, Step-Audio 2 delivers intelligence and expressiveness across diverse conversational scenarios. Evaluation results demonstrate that Step-Audio 2 achieves state-of-the-art performance on various audio understanding and conversational benchmarks compared to other open-source and commercial solutions. Please visit https://github.com/stepfun-ai/Step-Audio2 for more information.

Ailin Huang, Bingxin Li, Bruce Wang et al.

Large Audio-Language Models (LALMs) have significantly advanced intelligent human-computer interaction, yet their reliance on text-based outputs limits their ability to generate natural speech responses directly, hindering seamless audio interactions. To address this, we introduce Step-Audio-AQAA, a fully end-to-end LALM designed for Audio Query-Audio Answer (AQAA) tasks. The model integrates a dual-codebook audio tokenizer for linguistic and semantic feature extraction, a 130-billion-parameter backbone LLM and a neural vocoder for high-fidelity speech synthesis. Our post-training approach employs interleaved token-output of text and audio to enhance semantic coherence and combines Direct Preference Optimization (DPO) with model merge to improve performance. Evaluations on the StepEval-Audio-360 benchmark demonstrate that Step-Audio-AQAA excels especially in speech control, outperforming the state-of-art LALMs in key areas. This work contributes a promising solution for end-to-end LALMs and highlights the critical role of token-based vocoder in enhancing overall performance for AQAA tasks.

Weihao Wu, Liang Cao, Xinyu Wu et al.

Recent significant advancements in Large Language Models (LLMs) have greatly propelled the development of Role-Playing Conversational Agents (RPCAs). These systems aim to create immersive user experiences through consistent persona adoption. However, current RPCA research faces dual limitations. First, existing work predominantly focuses on the textual modality, entirely overlooking critical paralinguistic features including intonation, prosody, and rhythm in speech, which are essential for conveying character emotions and shaping vivid identities. Second, the speech-based role-playing domain suffers from a long-standing lack of standardized evaluation benchmarks. Most current spoken dialogue datasets target only fundamental capability assessments, featuring thinly sketched or ill-defined character profiles. Consequently, they fail to effectively quantify model performance on core competencies like long-term persona consistency. To address this critical gap, we introduce VoxRole, the first comprehensive benchmark specifically designed for the evaluation of speech-based RPCAs. The benchmark comprises 13335 multi-turn dialogues, totaling 65.6 hours of speech from 1228 unique characters across 261 movies. To construct this resource, we propose a novel two-stage automated pipeline that first aligns movie audio with scripts and subsequently employs an LLM to systematically build multi-dimensional profiles for each character. Leveraging VoxRole, we conduct a multi-dimensional evaluation of contemporary spoken dialogue models, revealing crucial insights into their respective strengths and limitations in maintaining persona consistency.

Weihao wu, Zhiwei Lin, Yixuan Zhou et al.

Conversational speech synthesis (CSS) aims to synthesize both contextually appropriate and expressive speech, and considerable efforts have been made to enhance the understanding of conversational context. However, existing CSS systems are limited to deterministic prediction, overlooking the diversity of potential responses. Moreover, they rarely employ language model (LM)-based TTS backbones, limiting the naturalness and quality of synthesized speech. To address these issues, in this paper, we propose DiffCSS, an innovative CSS framework that leverages diffusion models and an LM-based TTS backbone to generate diverse, expressive, and contextually coherent speech. A diffusion-based context-aware prosody predictor is proposed to sample diverse prosody embeddings conditioned on multimodal conversational context. Then a prosody-controllable LM-based TTS backbone is developed to synthesize high-quality speech with sampled prosody embeddings. Experimental results demonstrate that the synthesized speech from DiffCSS is more diverse, contextually coherent, and expressive than existing CSS systems

Jingbei Li, Yi Meng, Chenyi Li et al.

Comparing with traditional text-to-speech (TTS) systems, conversational TTS systems are required to synthesize speeches with proper speaking style confirming to the conversational context. However, state-of-the-art context modeling methods in conversational TTS only model the textual information in context with a recurrent neural network (RNN). Such methods have limited ability in modeling the inter-speaker influence in conversations, and also neglect the speaking styles and the intra-speaker inertia inside each speaker. Inspired by DialogueGCN and its superiority in modeling such conversational influences than RNN based approaches, we propose a graph-based multi-modal context modeling method and adopt it to conversational TTS to enhance the speaking styles of synthesized speeches. Both the textual and speaking style information in the context are extracted and processed by DialogueGCN to model the inter- and intra-speaker influence in conversations. The outputs of DialogueGCN are then summarized by attention mechanism, and converted to the enhanced speaking style for current utterance. An English conversation corpus is collected and annotated for our research and released to public. Experiment results on this corpus demonstrate the effectiveness of our proposed approach, which outperforms the state-of-the-art context modeling method in conversational TTS in both MOS and ABX preference rate.

Yixuan Zhou, Changhe Song, Jingbei Li et al.

Exploiting rich linguistic information in raw text is crucial for expressive text-to-speech (TTS). As large scale pre-trained text representation develops, bidirectional encoder representations from Transformers (BERT) has been proven to embody semantic information and employed to TTS recently. However, original or simply fine-tuned BERT embeddings still cannot provide sufficient semantic knowledge that expressive TTS models should take into account. In this paper, we propose a word-level semantic representation enhancing method based on dependency structure and pre-trained BERT embedding. The BERT embedding of each word is reprocessed considering its specific dependencies and related words in the sentence, to generate more effective semantic representation for TTS. To better utilize the dependency structure, relational gated graph network (RGGN) is introduced to make semantic information flow and aggregate through the dependency structure. The experimental results show that the proposed method can further improve the naturalness and expressiveness of synthesized speeches on both Mandarin and English datasets.

Xiang Li, Changhe Song, Jingbei Li et al.

This paper introduces a multi-scale speech style modeling method for end-to-end expressive speech synthesis. The proposed method employs a multi-scale reference encoder to extract both the global-scale utterance-level and the local-scale quasi-phoneme-level style features of the target speech, which are then fed into the speech synthesis model as an extension to the input phoneme sequence. During training time, the multi-scale style model could be jointly trained with the speech synthesis model in an end-to-end fashion. By applying the proposed method to style transfer task, experimental results indicate that the controllability of the multi-scale speech style model and the expressiveness of the synthesized speech are greatly improved. Moreover, by assigning different reference speeches to extraction of style on each scale, the flexibility of the proposed method is further revealed.

Jie Wang, Jingbei Li, Xintao Zhao et al.

Factorizing speech as disentangled speech representations is vital to achieve highly controllable style transfer in voice conversion (VC). Conventional speech representation learning methods in VC only factorize speech as speaker and content, lacking controllability on other prosody-related factors. State-of-the-art speech representation learning methods for more speechfactors are using primary disentangle algorithms such as random resampling and ad-hoc bottleneck layer size adjustment,which however is hard to ensure robust speech representationdisentanglement. To increase the robustness of highly controllable style transfer on multiple factors in VC, we propose a disentangled speech representation learning framework based on adversarial learning. Four speech representations characterizing content, timbre, rhythm and pitch are extracted, and further disentangled by an adversarial Mask-And-Predict (MAP)network inspired by BERT. The adversarial network is used tominimize the correlations between the speech representations,by randomly masking and predicting one of the representationsfrom the others. Experimental results show that the proposedframework significantly improves the robustness of VC on multiple factors by increasing the speech quality MOS from 2.79 to3.30 and decreasing the MCD from 3.89 to 3.58.

Changhe Song, Jingbei Li, Yixuan Zhou et al.

Syntactic structure of a sentence text is correlated with the prosodic structure of the speech that is crucial for improving the prosody and naturalness of a text-to-speech (TTS) system. Nowadays TTS systems usually try to incorporate syntactic structure information with manually designed features based on expert knowledge. In this paper, we propose a syntactic representation learning method based on syntactic parse tree traversal to automatically utilize the syntactic structure information. Two constituent label sequences are linearized through left-first and right-first traversals from constituent parse tree. Syntactic representations are then extracted at word level from each constituent label sequence by a corresponding uni-directional gated recurrent unit (GRU) network. Meanwhile, nuclear-norm maximization loss is introduced to enhance the discriminability and diversity of the embeddings of constituent labels. Upsampled syntactic representations and phoneme embeddings are concatenated to serve as the encoder input of Tacotron2. Experimental results demonstrate the effectiveness of our proposed approach, with mean opinion score (MOS) increasing from 3.70 to 3.82 and ABX preference exceeding by 17% compared with the baseline. In addition, for sentences with multiple syntactic parse trees, prosodic differences can be clearly perceived from the synthesized speeches.

Xiong Cai, Dongyang Dai, Zhiyong Wu et al.

Neural text-to-speech (TTS) approaches generally require a huge number of high quality speech data, which makes it difficult to obtain such a dataset with extra emotion labels. In this paper, we propose a novel approach for emotional TTS synthesis on a TTS dataset without emotion labels. Specifically, our proposed method consists of a cross-domain speech emotion recognition (SER) model and an emotional TTS model. Firstly, we train the cross-domain SER model on both SER and TTS datasets. Then, we use emotion labels on the TTS dataset predicted by the trained SER model to build an auxiliary SER task and jointly train it with the TTS model. Experimental results show that our proposed method can generate speech with the specified emotional expressiveness and nearly no hindering on the speech quality.