This research introduces an innovative voice-assisted debugging plugin for Python that transforms silent runtime errors into actionable audible diagnostics. By implementing a global exception hook architecture with pyttsx3 text-to-speech conversion and Tkinter-based GUI visualization, the solution delivers multimodal error feedback through parallel auditory and visual channels. Empirical evaluation demonstrates 37% reduced cognitive load (p<0.01, n=50) compared to traditional stack-trace debugging, while enabling 78% faster error identification through vocalized exception classification and contextualization. The system achieves sub-1.2 second voice latency with under 18% CPU overhead during exception handling, vocalizing error types and consequences while displaying interactive tracebacks with documentation deep links. Criteria validate compatibility across Python 3.7+ environments on Windows, macOS, and Linux platforms. Needing only two lines of integration code, the plugin significantly boosts availability for aesthetically impaired designers and supports multitasking workflows through hands-free error medical diagnosis. Educational applications show particular promise, with pilot studies indicating 45% faster debugging skill acquisition among novice programmers. Future development will incorporate GPT-based repair suggestions and real-time multilingual translation to further advance auditory debugging paradigms. The solution represents a fundamental shift toward human-centric error diagnostics, bridging critical gaps in programming accessibility while establishing new standards for cognitive efficiency in software development workflows.
Current expressive speech synthesis models are constrained by the limited availability of open-source datasets containing diverse nonverbal vocalizations (NVs). In this work, we introduce NonverbalTTS (NVTTS), a 17-hour open-access dataset annotated with 10 types of NVs (e.g., laughter, coughs) and 8 emotional categories. The dataset is derived from popular sources, VoxCeleb and Expresso, using automated detection followed by human validation. We propose a comprehensive pipeline that integrates automatic speech recognition (ASR), NV tagging, emotion classification, and a fusion algorithm to merge transcriptions from multiple annotators. Fine-tuning open-source text-to-speech (TTS) models on the NVTTS dataset achieves parity with closed-source systems such as CosyVoice2, as measured by both human evaluation and automatic metrics, including speaker similarity and NV fidelity. By releasing NVTTS and its accompanying annotation guidelines, we address a key bottleneck in expressive TTS research. The dataset is available at https://huggingface.co/datasets/deepvk/NonverbalTTS.
Generating expressive audio performances from music scores requires models to capture both instrument acoustics and human interpretation. Traditional music performance synthesis pipelines follow a two-stage approach, first generating expressive performance MIDI from a score, then synthesising the MIDI into audio. However, the synthesis models often struggle to generalise across diverse MIDI sources, musical styles, and recording environments. To address these challenges, we propose MIDI-VALLE, a neural codec language model adapted from the VALLE framework, which was originally designed for zero-shot personalised text-to-speech (TTS) synthesis. For performance MIDI-to-audio synthesis, we improve the architecture to condition on a reference audio performance and its corresponding MIDI. Unlike previous TTS-based systems that rely on piano rolls, MIDI-VALLE encodes both MIDI and audio as discrete tokens, facilitating a more consistent and robust modelling of piano performances. Furthermore, the model's generalisation ability is enhanced by training on an extensive and diverse piano performance dataset. Evaluation results show that MIDI-VALLE significantly outperforms a state-of-the-art baseline, achieving over 75% lower Frechet Audio Distance on the ATEPP and Maestro datasets. In the listening test, MIDI-VALLE received 202 votes compared to 58 for the baseline, demonstrating improved synthesis quality and generalisation across diverse performance MIDI inputs.
Advancements in artificial intelligence (AI) have significantly enhanced the realism and interactivity of non-player characters (NPCs) in virtual reality (VR), creating more engaging and believable user experiences. This paper evaluates AI-driven NPCs within a VR interrogation simulator, focusing on their perceived realism, usability, and system performance. The simulator features two AI-powered NPCs, a suspect, and a partner, using GPT-4 Turbo to engage participants in a scenario to determine the suspect's guilt or innocence. A user study with 18 participants assessed the system using the System Usability Scale (SUS), Game Experience Questionnaire (GEQ), and a Virtual Agent Believability Questionnaire, alongside latency measurements for speech-to-text (STT), text-to-speech (TTS), OpenAI GPT-4 Turbo, and overall (cycle) latency. Results showed an average cycle latency of 7 seconds, influenced by the increasing conversational context. Believability scored 6.67 out of 10, with high ratings in behavior, social relationships, and intelligence but moderate scores in emotion and personality. The system achieved a SUS score of 79.44, indicating good usability. These findings demonstrate the potential of large language models to improve NPC realism and interaction in VR while highlighting challenges in reducing system latency and enhancing emotional depth. This research contributes to the development of more sophisticated AI-driven NPCs, revealing the need for performance optimization to achieve increasingly immersive virtual experiences.
In speech quality estimation for speech enhancement (SE) systems, subjective listening tests so far are considered as the gold standard. This should be even more true considering the large influx of new generative or hybrid methods into the field, revealing issues of some objective metrics. Efforts such as the Interspeech 2025 URGENT Speech Enhancement Challenge also involving non-English datasets add the aspect of multilinguality to the testing procedure. In this paper, we provide a brief recap of the ITU-T P.808 crowdsourced subjective listening test method. A first novel contribution is our proposed process of localizing both text and audio components of Naderi and Cutler's implementation of crowdsourced subjective absolute category rating (ACR) listening tests involving text-to-speech (TTS). Further, we provide surprising analyses of and insights into URGENT Challenge results, tackling the reliability of (P.808) ACR subjective testing as gold standard in the age of generative AI. Particularly, it seems that for generative SE methods, subjective (ACR MOS) and objective (DNSMOS, NISQA) reference-free metrics should be accompanied by objective phone fidelity metrics to reliably detect hallucinations. Finally, in the accepted version, we will release our localization scripts and methods for easy deployment for new multilingual speech enhancement subjective evaluations according to ITU-T P.808.
While poisoning attacks on machine learning models have been extensively studied, the mechanisms by which adversaries can distribute poisoned models at scale remain largely unexplored. In this paper, we shed light on how model leaderboards -- ranked platforms for model discovery and evaluation -- can serve as a powerful channel for adversaries for stealthy large-scale distribution of poisoned models. We present TrojanClimb, a general framework that enables injection of malicious behaviors while maintaining competitive leaderboard performance. We demonstrate its effectiveness across four diverse modalities: text-embedding, text-generation, text-to-speech and text-to-image, showing that adversaries can successfully achieve high leaderboard rankings while embedding arbitrary harmful functionalities, from backdoors to bias injection. Our findings reveal a significant vulnerability in the machine learning ecosystem, highlighting the urgent need to redesign leaderboard evaluation mechanisms to detect and filter malicious (e.g., poisoned) models, while exposing broader security implications for the machine learning community regarding the risks of adopting models from unverified sources.
Generating spoken dialogue is more challenging than monologue text-to-speech (TTS) due to the need for realistic turn-taking and distinct speaker timbres. Existing spoken dialogue generation models, being auto-regressive, suffer from slow and unstable inference. To overcome these limitations, we introduce ZipVoice-Dialog, a non-autoregressive zero-shot spoken dialogue generation model built upon flow matching. Key designs include: 1) speaker-turn embeddings for precise speaker turn-taking; 2) a curriculum learning strategy for stable speech-text alignment; 3) specialized strategies to enable stereo dialogue generation. Additionally, recognizing the lack of open-source large-scale spoken dialogue datasets, we curated OpenDialog, a 6.8k-hour spoken dialogue dataset from in-the-wild speech data. Furthermore, we established a benchmark to comprehensively evaluate various models. Experimental results demonstrate that ZipVoice-Dialog achieves superior performance in intelligibility, speaker turn-taking accuracy, speaker similarity, and inference speed. Our codes, model checkpoints, demo samples, and the OpenDialog dataset are all publicly available at https://github.com/k2-fsa/ZipVoice.
This paper proposes a novel Differentiable Reward Optimization (DiffRO) method aimed at enhancing the performance of neural codec language models based text-to-speech (TTS) systems. In contrast to conventional reinforcement learning from human feedback (RLHF) approaches applied to TTS, DiffRO directly compute the rewards based on neural codec tokens, rather than relying on synthesized audio. Furthermore, we employ the Gumbel-Softmax technique to render the reward function differentiable, thereby streamlining the RLHF training process. Additionally, we introduce a multi-task reward (MTR) model which can provide feedback from different perspectives and find that it can augment the system's capability to follow instructions effectively.Experimental results indicate that DiffRO significantly improves the pronunciation accuracy of the TTS system, achieving state-of-the-art (SOTA) WER results on the seed-tts-eval benchmark. Moreover, with the integration of the MTR model, we demonstrate the ability to control emotional and quality attributes in a zero-shot manner.
Automatic speech quality assessment plays a crucial role in the development of speech synthesis systems, but existing models exhibit significant performance variations across different granularity levels of prediction tasks. This paper proposes an enhanced MOS prediction system based on self-supervised learning speech models, incorporating a Mixture of Experts (MoE) classification head and utilizing synthetic data from multiple commercial generation models for data augmentation. Our method builds upon existing self-supervised models such as wav2vec2, designing a specialized MoE architecture to address different types of speech quality assessment tasks. We also collected a large-scale synthetic speech dataset encompassing the latest text-to-speech, speech conversion, and speech enhancement systems. However, despite the adoption of the MoE architecture and expanded dataset, the model's performance improvements in sentence-level prediction tasks remain limited. Our work reveals the limitations of current methods in handling sentence-level quality assessment, provides new technical pathways for the field of automatic speech quality assessment, and also delves into the fundamental causes of performance differences across different assessment granularities.
Autonomous agents for Graphical User Interfaces (GUIs) are revolutionizing human-computer interaction, yet their reliance on text-based instructions imposes limitations on accessibility and convenience, particularly in hands-free scenarios. To address this gap, we propose GUIRoboTron-Speech, the first end-to-end autonomous GUI agent that directly accepts speech instructions and on-device screenshots to predict actions. Confronted with the scarcity of speech-based GUI agent datasets, we initially generated high-quality speech instructions for training by leveraging a random timbre text-to-speech (TTS) model to convert existing text instructions. We then develop GUIRoboTron-Speech's capabilities through progressive grounding and planning training stages. A key contribution is a heuristic mixed-instruction training strategy designed to mitigate the modality imbalance inherent in pre-trained foundation models. Comprehensive experiments on several benchmark datasets validate the robust and superior performance of GUIRoboTron-Speech, demonstrating the significant potential and widespread applicability of speech as an effective instruction modality for driving GUI agents. Our code and datasets are available at https://github.com/GUIRoboTron/GUIRoboTron-Speech.
We present PresentAgent, a multimodal agent that transforms long-form documents into narrated presentation videos. While existing approaches are limited to generating static slides or text summaries, our method advances beyond these limitations by producing fully synchronized visual and spoken content that closely mimics human-style presentations. To achieve this integration, PresentAgent employs a modular pipeline that systematically segments the input document, plans and renders slide-style visual frames, generates contextual spoken narration with large language models and Text-to-Speech models, and seamlessly composes the final video with precise audio-visual alignment. Given the complexity of evaluating such multimodal outputs, we introduce PresentEval, a unified assessment framework powered by Vision-Language Models that comprehensively scores videos across three critical dimensions: content fidelity, visual clarity, and audience comprehension through prompt-based evaluation. Our experimental validation on a curated dataset of 30 document-presentation pairs demonstrates that PresentAgent approaches human-level quality across all evaluation metrics. These results highlight the significant potential of controllable multimodal agents in transforming static textual materials into dynamic, effective, and accessible presentation formats. Code will be available at https://github.com/AIGeeksGroup/PresentAgent.
We introduce RapFlow-TTS, a rapid and high-fidelity TTS acoustic model that leverages velocity consistency constraints in flow matching (FM) training. Although ordinary differential equation (ODE)-based TTS generation achieves natural-quality speech, it typically requires a large number of generation steps, resulting in a trade-off between quality and inference speed. To address this challenge, RapFlow-TTS enforces consistency in the velocity field along the FM-straightened ODE trajectory, enabling consistent synthetic quality with fewer generation steps. Additionally, we introduce techniques such as time interval scheduling and adversarial learning to further enhance the quality of the few-step synthesis. Experimental results show that RapFlow-TTS achieves high-fidelity speech synthesis with a 5- and 10-fold reduction in synthesis steps than the conventional FM- and score-based approaches, respectively.
There has been limited evaluation of advanced Text-to-Speech (TTS) models with Mathematical eXpressions (MX) as inputs. In this work, we design experiments to evaluate quality and intelligibility of five TTS models through listening and transcribing tests for various categories of MX. We use two Large Language Models (LLMs) to generate English pronunciation from LaTeX MX as TTS models cannot process LaTeX directly. We use Mean Opinion Score from user ratings and quantify intelligibility through transcription correctness using three metrics. We also compare listener preference of TTS outputs with respect to human expert rendition of same MX. Results establish that output of TTS models for MX is not necessarily intelligible, the gap in intelligibility varies across TTS models and MX category. For most categories, performance of TTS models is significantly worse than that of expert rendition. The effect of choice of LLM is limited. This establishes the need to improve TTS models for MX.
Zero-shot multi-speaker text-to-speech (TTS) systems rely on speaker embeddings to synthesize speech in the voice of an unseen speaker, using only a short reference utterance. While many speaker embeddings have been developed for speaker recognition, their relative effectiveness in zero-shot TTS remains underexplored. In this work, we employ a YourTTS-based TTS system to compare three different speaker encoders - YourTTS's original H/ASP encoder, x-vector embeddings, and ECAPA-TDNN embeddings - within an otherwise fixed zero-shot TTS framework. All models were trained on the same dataset of Czech read speech and evaluated on 24 out-of-domain target speakers using both subjective and objective methods. The subjective evaluation was conducted via a listening test focused on speaker similarity, while the objective evaluation measured cosine distances between speaker embeddings extracted from synthesized and real utterances. Across both evaluations, the original H/ASP encoder consistently outperformed the alternatives, with ECAPA-TDNN showing better results than x-vectors. These findings suggest that, despite the popularity of ECAPA-TDNN in speaker recognition, it does not necessarily offer improvements for speaker similarity in zero-shot TTS in this configuration. Our study highlights the importance of empirical evaluation when reusing speaker recognition embeddings in TTS and provides a framework for additional future comparisons.
Evaluation of Text to Speech (TTS) systems is challenging and resource-intensive. Subjective metrics such as Mean Opinion Score (MOS) are not easily comparable between works. Objective metrics are frequently used, but rarely validated against subjective ones. Both kinds of metrics are challenged by recent TTS systems capable of producing synthetic speech indistinguishable from real speech. In this work, we introduce Text to Speech Distribution Score 2 (TTSDS2), a more robust and improved version of TTSDS. Across a range of domains and languages, it is the only one out of 16 compared metrics to correlate with a Spearman correlation above 0.50 for every domain and subjective score evaluated. We also release a range of resources for evaluating synthetic speech close to real speech: A dataset with over 11,000 subjective opinion score ratings; a pipeline for continually recreating a multilingual test dataset to avoid data leakage; and a continually updated benchmark for TTS in 14 languages.
With the rapid progress of speech language models (SLMs), discrete speech tokens have emerged as a core interface between speech and text, enabling unified modeling across modalities. Recent speech tokenization approaches aim to isolate semantic information from low-level acoustics to better align with language models. In particular, previous methods use SSL teachers such as HuBERT to extract semantic representations, which are then distilled into a semantic quantizer to suppress acoustic redundancy as well as capture content-related latent structures. However, they still produce speech token sequences significantly longer than their textual counterparts, creating challenges for efficient speech-language modeling. Reducing the frame rate is a natural solution, but standard techniques, such as rigid average pooling across frames, can distort or dilute the semantic structure required for effective LM alignment. To address this, we propose LM-SPT, a speech tokenization method that introduces a novel semantic distillation. Instead of directly matching teacher and student features via pooling, we reconstruct speech solely from semantic tokens and minimize the discrepancy between the encoded representations of the original and reconstructed waveforms, obtained from a frozen automatic speech recognition (ASR) encoder. This indirect yet data-driven supervision enables the tokenizer to learn discrete units that are more semantically aligned with language models. LM-SPT further incorporates architectural improvements to the encoder and decoder for speech tokenization, and supports multiple frame rates, including 25Hz, 12.5Hz, and 6.25Hz. Experimental results show that LM-SPT achieves superior reconstruction fidelity compared to baselines, and that SLMs trained with LM-SPT tokens achieve competitive performances on speech-to-text and consistently outperform baselines on text-to-speech tasks.
We propose a first streaming accent conversion (AC) model that transforms non-native speech into a native-like accent while preserving speaker identity, prosody and improving pronunciation. Our approach enables stream processing by modifying a previous AC architecture with an Emformer encoder and an optimized inference mechanism. Additionally, we integrate a native text-to-speech (TTS) model to generate ideal ground-truth data for efficient training. Our streaming AC model achieves comparable performance to the top AC models while maintaining stable latency, making it the first AC system capable of streaming.
In modern speech synthesis, paralinguistic information--such as a speaker's vocal timbre, emotional state, and dynamic prosody--plays a critical role in conveying nuance beyond mere semantics. Traditional Text-to-Speech (TTS) systems rely on fixed style labels or inserting a speech prompt to control these cues, which severely limits flexibility. Recent attempts seek to employ natural-language instructions to modulate paralinguistic features, substantially improving the generalization of instruction-driven TTS models. Although many TTS systems now support customized synthesis via textual description, their actual ability to interpret and execute complex instructions remains largely unexplored. In addition, there is still a shortage of high-quality benchmarks and automated evaluation metrics specifically designed for instruction-based TTS, which hinders accurate assessment and iterative optimization of these models. To address these limitations, we introduce InstructTTSEval, a benchmark for measuring the capability of complex natural-language style control. We introduce three tasks, namely Acoustic-Parameter Specification, Descriptive-Style Directive, and Role-Play, including English and Chinese subsets, each with 1k test cases (6k in total) paired with reference audio. We leverage Gemini as an automatic judge to assess their instruction-following abilities. Our evaluation of accessible instruction-following TTS systems highlights substantial room for further improvement. We anticipate that InstructTTSEval will drive progress toward more powerful, flexible, and accurate instruction-following TTS.
Large Language Models (LLMs) are widely used in real-time voice chat applications, typically in combination with text-to-speech (TTS) systems to generate audio responses. However, their large size often leads to noticeable latency between the end of user input and the start of audio output, resulting in suboptimal user experiences. This latency is particularly evident when LLMs are deployed as single-user voice assistants on consumer-grade hardware with limited computing capacity. We discovered that this latency is primarily dominated by the time it takes for the LLMs to generate the first sentence, which is required as input by the TTS systems that synthesize audio responses on a sentence-by-sentence basis. To address this bottleneck, we propose Predictive Generation (PredGen), a novel framework that mitigates-or even eliminates-this delay through speculative decoding at input time. PredGen generates candidate responses while the user is still speaking, enabling the system to begin TTS processing with minimal delay. Simulated experiments on the Lmsys and MT-Bench datasets show that the proposed method can effectively reduce the latency by around 2x across a wide range of use cases, while incurring only minimal additional computation cost at input time-computation that would otherwise go unused.
State-of-the-art text-to-speech (TTS) systems realize high naturalness in monolingual environments, synthesizing speech with correct multilingual accents (especially for Indic languages) and context-relevant emotions still poses difficulty owing to cultural nuance discrepancies in current frameworks. This paper introduces a new TTS architecture integrating accent along with preserving transliteration with multi-scale emotion modelling, in particularly tuned for Hindi and Indian English accent. Our approach extends the Parler-TTS model by integrating A language-specific phoneme alignment hybrid encoder-decoder architecture, and culture-sensitive emotion embedding layers trained on native speaker corpora, as well as incorporating a dynamic accent code switching with residual vector quantization. Quantitative tests demonstrate 23.7% improvement in accent accuracy (Word Error Rate reduction from 15.4% to 11.8%) and 85.3% emotion recognition accuracy from native listeners, surpassing METTS and VECL-TTS baselines. The novelty of the system is that it can mix code in real time - generating statements such as "Namaste, let's talk about <Hindi phrase>" with uninterrupted accent shifts while preserving emotional consistency. Subjective evaluation with 200 users reported a mean opinion score (MOS) of 4.2/5 for cultural correctness, much better than existing multilingual systems (p<0.01). This research makes cross-lingual synthesis more feasible by showcasing scalable accent-emotion disentanglement, with direct application in South Asian EdTech and accessibility software.