In low-resource settings, deploying TTS typically requires choosing between a large voice-cloning model with costly inference or a compact fixed-voice system that requires a speaker-specific corpus. We study a third route: using a large voice-cloning model as a programmable data source to turn a short voice reference (e.g., 15 seconds) into a compact fixed-voice student trained entirely on synthetic speech. This setting makes pipeline design consequential: teacher errors become training targets, while filtering failed generations can reduce coverage of difficult texts. Thai further introduces challenges from ambiguous word boundaries, lexical tone, names and loanwords, numeric verbalization, and Thai-English code-switching. We study how text preparation, synthetic generation, quality filtering, rejection sampling, and frontend choices affect the resulting student, and where teacher limitations remain. We evaluate CER, Challenge-Set Keyword Accuracy, Prosody Pause Accuracy, speaker similarity, and speaking rate. The resulting 82M-parameter model, Wayu-Paxa-TTS-Edge, enables on-device Thai TTS without reference audio. It achieves 68.2% Challenge-Set Keyword Accuracy (85.5% of Gemini 3.1) and 91.4% pause precision, outperforming its OmniVoice teacher (89.9%) and reaching 94.8% of Gemini 3.1. It also achieves the lowest pause-placement error and intra-word pause rates among the three systems, and 3.7% and 1.1% CER on Thai and English, respectively. We open-source the model and evaluation framework for Thai TTS development.
Voice actors often re-read the same script while modifying their delivery in response to performance directions. We study this setting as direction-following TTS, where a system generates a new utterance that reflects a given direction relative to a reference utterance while preserving speaker identity and linguistic content. A key challenge is the lack of training data capturing such relative modifications. To address this, we propose a scalable pseudo-triplet construction pipeline that generates~(reference utterance, direction text, modified utterance) triplets. It generates controlled style variations using an impression-controllable TTS model and uses an LLM to produce natural language directions from estimated impression differences. Experimental results demonstrate that pseudo-triplets alone enable stable speaker-preserving modification, and that combining pseudo and recorded data further improves direction alignment while maintaining speaker similarity. Audio examples are available on our demo page https://ntt-hilab-gensp.github.io/IS2026pseudo/
Text-to-Speech (TTS) foundation models are increasingly fine-tuned on private datasets to synthesize highly personalized voices, introducing severe privacy risks by exposing both biometric identities and sensitive speech content. Existing black-box membership inference attacks (MIAs) follow a two-stage pipeline of query generation and representation engineering, both of which face unique challenges when adapted to TTS. For query generation, dual conditioning on synthesis text and reference speech creates a large and underexplored query design space with no established criterion for identifying an effective query. For representation engineering, the multi-level speech characteristics and temporal variability of speech make low-level representations and direct comparisons inadequate for capturing membership signals. To address these challenges, we present the first black-box MIA framework explicitly tailored to TTS models at both the speaker and record levels. For query generation, we characterize the feasible query space and establish two criteria, scorable extent and memorization elicitation, for evaluating five representative queries, identifying recitation as the strongest. For representation engineering, we obtain multi-level speech representations from embedding models and temporally align the generated and target audio for fine-grained comparison. Evaluations across three state-of-the-art TTS models (CosyVoice2, F5-TTS, and XTTS-v2) fine-tuned on two benchmark datasets (VCTK and British Dialect) reveal severe privacy leakage: speaker-level AUC remains above 0.80 and approaches 1.0 in the strongest settings, while record-level AUC ranges from 0.80 to 0.90 and remains effective even in challenging scenarios where both members and non-members are of the same speakers. We further identify speech characteristics associated with disproportionate vulnerability to memorization.
Current Large Language Models (LLMs) are primarily optimized for written text, often producing outputs that are grammatically correct and helpful yet poorly suited for spoken delivery via Text-to-Speech (TTS). In this work, we study how to make LLMs natively generate TTS-friendly text, which we frame as a preference alignment problem: instead of relying on downstream rewriting modules, we directly align LLMs to generate text optimized for spoken delivery. We introduce two preference datasets spanning different target domains, CORA and Recipe, which contain paired TTS-friendly and TTS-unfriendly responses. We further propose an evaluation suite combining a pattern-based heuristic metric, a TTS$\to$ASR evaluation pipeline, and a MUSHRA listening study with human judges. Our experiments compare the recently proposed Feature-aware Sampling and Tuning (FaST) framework -- leveraging interpretable features instead of a black-box reward model -- against an array of alignment baselines on the TTS-friendly generation task. Notably, we found that FaST achieves the best overall tradeoff between TTS-friendliness and helpfulness across various settings. We also identified a strong correlation between our different metrics, highlighting the ability to reliably assess TTS-friendliness via an efficient heuristic.
Che Hyun Lee, Sangkwon Park, Donghun Kang +4cs.CL cs.SD
Current speech synthesis struggles with code-switching, which mixes a foreign language phrase into a primary language utterance, causing the phrase to be spoken with the primary language's accent rather than its native one. We propose Phrase-Localized Language-Contrastive Guidance (LCG), a training-free inference framework that restores a native accent to code-switched phrases in cross-lingual text-to-speech. LCG replaces the single language guidance applied across the whole utterance with a separate guidance for each region, so each part is guided by its own language. To choose where to apply this localized guidance, we propose a self-attention probing technique that finds the phrase boundaries without external alignments. Together, these components generate speech in which each region carries the accent of its own language, requiring no fine-tuning or auxiliary models. Across diverse language pairs, LCG robustly increases the nativeness of the code-switched phrase while suppressing accent leakage, and preserving overall speaker identity and naturalness.
Codec-based text-to-speech (TTS) models make language-model post-training applicable to speech generation, but it remains unclear when learned perceptual predictors can serve as reinforcement learning rewards without losing alignment with human listeners. We study this question with Group Relative Policy Optimization (GRPO) using learned rewards for anime-like speaking style, naturalness, likability, and arousal. To prevent perceptual rewards from being optimized through transcript drift, we introduce a character error rate (CER) zone constraint and compare policy optimization with Best-of-$N$ reranking under the same reward gate. Across single-reward runs, each reward primarily improves its own target metric, showing that subjective predictors are not interchangeable quality surrogates. Multi-rater A/B tests further show uneven human transfer, while a reward-gap analysis separates average transfer from within-axis calibration: signed reward gaps significantly predict listener choices in the pooled analysis, whereas residual CER gaps do not, but per-axis calibration remains heterogeneous. Best-of-8 is a strong human-level baseline and is not clearly worse than GRPO perceptually, suggesting that GRPO should be viewed as amortizing reward-selected behavior into the policy rather than uniformly outperforming reranking. These results support analyzing subjective speech rewards as predictor-axis-base tuples and provide practical diagnostics for selecting rewards before multi-reward speech post-training.
Zeyang Song, Tianchi Liu, Tianrui Wang +3cs.SD cs.AI
Current TTS systems typically rely on open-loop, single-pass generation and can produce sporadic local prosodic defects, such as misplaced stress, unnatural pauses, or flattened intonation, that utterance-level metrics often fail to expose. We present LoopTTS, a judge-guided Filter-Judge-Refiner framework for recovering low-quality TTS outputs diagnosed by an AudioLLM. Given an initial utterance from a base TTS model, an AudioLLM Judge identifies salient prosodic issues and generates structured refine instructions; a Refiner, our fine-grained instruction-following TTS model, then performs guided expressive re-synthesis conditioned on the initial utterance, target text, and instruction. To train the Refiner, we construct Refiner-DB, a 42K-example AudioLLM-annotated dataset with word-level prosodic weak supervision. Human evaluation on diagnosed low-quality utterances shows that LoopTTS can detect perceptually salient errors and correct them with the Refiner, outperforming raw generated audio and practical open-loop re-generation baselines in recovery quality. The Refiner also demonstrates stronger instruction-following ability for stress and pause control in targeted prosody modification.
Non-verbal vocalizations (NVs), such as laughter, coughs, and sighs, are essential for expressive TTS, but the effectiveness of preference optimization for NV generation remains poorly understood. We systematically study preference optimization for NV-capable TTS, focusing on preference signals, preference-pair construction, and DPO-based optimization objectives. We formulate an NV-aware character error rate (NV-CER) by treating NV tags as distinct output symbols and computing a weighted pinyin-based CER over both verbal and non-verbal content, enabling controllable optimization of NV realization without modifying the underlying optimization algorithm. Experiments on Emilia-NV and the augmented NV-Bench covering 18 NV types reveal how different design choices affect NV realization and lexical fidelity, and establish an effective setup using standard DPO. Objective, LLM-based, and human evaluations provide converging evidence for our findings, offering practical insights into NV-aware post-training for expressive TTS.
Synthetic conversational speech has become an important resource for developing and evaluating conversational speech systems. However, existing dialogue synthesis pipelines typically generate dialogue content first and then insert interruptions, overlap, and backchannels using handcrafted markers or timing rules, making conversational timing prescribed rather than interaction-driven. We present DuplexGen, a dialogue synthesis framework that explicitly decouples content, timing, and acoustics. An LLM first generates the dialogue script, and then two full-duplex conversational models perform the script while listening to each other in real time. This allows conversational timing to emerge naturally while preserving the scripted content. Finally, a high-fidelity text-to-speech model re-renders the interaction without altering its timing. As a demonstration of the proposed framework, we construct a patient--clinician conversational speech corpus with construction-time annotations, including word timestamps, speaker activity, overlap regions, and interaction events. Experimental results show that the proposed framework produces conversational dynamics closer to real dialogue than conventional stitching-based synthesis.
Nicholas Sanders, Gustav Eje Henter, Simon King +1eess.AS cs.CL cs.SD
Expressive text-to-speech (TTS) systems that use explicit conditioning labels provide direct and interpretable control over expressive attributes, in contrast to reference-based or prompting-based approaches, but require labeled data. Obtaining these labels at scale is costly and time-consuming, yet no prior semi-supervised framework addresses this specific bottleneck. Existing semi-supervised TTS methods instead target scarcity of paired speech-text data or transcriptions. To address the scarcity of expressive labels, we propose an Iterative Self-Learning (ISL) framework for expressive TTS, built on Invert-Classify, a classifier-free method that recovers discrete expressive labels by inverting a frozen generative model. The framework iteratively pseudo-labels unlabeled speech using the current model, retrains on the combined labeled and pseudo-labeled data, and repeats, progressively refining label quality and synthesis. We validate on two expressive tasks, word-level prominence and utterance-level emotion, across multiple low-resource data splits. We find that iterative refinement can improve pseudo-label accuracy over single-pass baselines. Furthermore, we observe that these improvements in pseudo-labeling of expressivity translate to gains in expressive label adherence and synthesis quality, confirmed by objective metrics and human listening tests. In the most data-scarce conditions, ISL-trained models outperform single-pass pseudo-labeling and further approach fully supervised performance, demonstrating that gradient-based ISL is an effective solution to expressive label scarcity in low-resource TTS.
Live game commentary is scarce: it exists for professional esports broadcasts and almost nowhere else. We present a content-based video narration system that produces spoken, esports-style commentary for arbitrary gameplay recordings using a general-purpose vision-language model (VLM) and a text-to-speech back end, with no game-specific instrumentation, no engine telemetry, and no task-specific training. Three mechanisms carry the system. Temporal mosaic packing arranges nine uniformly sampled frames into a single 3x3 image, letting an image-native VLM reason about motion while consuming one image payload per segment instead of nine. Context-conditioned prompting replays the K most recent narrations as assistant-role history, suppressing the repetition that dominates per-segment captioning of static scenes. Duration-conditioned generation and elastic alignment constrain narration length in the prompt, then time-scale or symmetrically pad the synthesized audio so each utterance fills its segment slot exactly, giving frame-accurate muxing without a forced aligner. The implementation supports either cloud TTS or a 6-bit quantized 4B-parameter on-device TTS model on Apple silicon, making the speech stage fully local. We report a qualitative case study on real-time strategy footage, a cost model showing the mosaic reduces per-minute image payloads by 9x, and a candid account of observed failure modes - hallucinated game state, resolution loss from mosaicking, and prosody artifacts from time-scaling. We release the system as a reproducible baseline, with an evaluation protocol for the quantitative study a full version will report.
Edresson Casanova, Jaehyeon Kim, Mariana Graterol Fuenmayor +17eess.AS cs.CL
Spoken dialogue is a natural form of human--computer interaction, yet most speech language models remain limited to turn-based operation and lack real-time adaptability, such as user barge-in. Recent duplex speech-to-speech and speech-to-text models reduce latency by replacing multi-stage pipelines, but often compromise speech quality because accurate ASR, interruption handling, and high-fidelity synthesis must be optimized jointly. We propose VoiceChat-TTS, a low-latency, continuous, and streamable text-to-speech model for interactive agents. VoiceChat-TTS is driven directly by LLM text-token streams, supports explicit interruption via control tokens, and produces silence when no textual input is available. The model enables always-on, responsive speech generation while preserving modularity and high speech quality, and it supports mid-utterance interruptions without resetting the KV cache.
FastThaiG2P provides sub-millisecond Thai grapheme-to-phoneme conversion for text-to-speech pipelines (International Phonetic Alphabet and Kokoro-TTS conventions) using a PyThaiNLP-tokenized, extensible dictionary and normalization rules for common Central Thai speech. The approach achieves an average latency of 0.15 ms per utterance on a benchmark of 27,242 synthetically generated utterances, of which 30\% is spent on tokenization, 12\% on normalization, and 58\% on out-of-vocabulary fallbacks (0.5\% OOV rate). To demonstrate its effectiveness, we used FastThaiG2P to phonemize Som-TTS, an open dataset containing 20 hours of grapheme-and-audio pairs, then trained an 82M-parameter StyleTTS 2 model based on a Kokoro-TTS recipe. The resulting model vocalizes intelligible Thai speech suitable for prototyping and development at 0.25 real-time factor (4x real-time) with ONNX inference on CPU.
Human voice generation has made rapid progress in speech generation, singing voice generation, voice cloning, and voice editing. However, most existing systems are designed for specific tasks and often rely on task-dependent architectures, control signals, or autoregressive decoding, limiting fine-grained controllability and inference efficiency. In this paper, we propose CookVoice, a unified framework for multimodal, multi-style, and multi-task human voice generation. CookVoice decomposes the human voice into three key factors: content, prosody, and style, enabling both speech and singing voice generation within a unified model. To achieve precise and flexible controllability, we design a flexible alignment strategy that maps text, style, and prosody control signals onto the frame-level of spectrogram. This design allows CookVoice to support a wide range of tasks, including text-to-speech, text-to-singing voice, style-controllable generation, voice mimicry, voice conversion, and voice editing. Experimental results show that CookVoice achieves generation quality comparable to existing Text-to-Speech and text-to-singing voice baselines, while providing stronger style and prosody controllability. Moreover, CookVoice achieves comparable performance to large-scale baselines with only 43.51 million parameters and efficient inference using as few as 4 ODE steps, making it a practical solution for real-world human voice generation applications. Demo page is available at https://haoweilou.github.io/CookVoice/.
ASR-roundtrip evaluation is widely used as a scalable proxy for text-to-speech (TTS) intelligibility, but it can produce false negatives for reading errors perceived by listeners. We study Chinese news TTS spans whose correct reading depends on context or domain conventions, such as sports scores, aircraft models, technical units, and membership names. In these cases, Raw TTS can choose a plausible but wrong reading while ASR transcribes the audio as the intended or surface-correct text. A targeted audit over 110 high-risk MiMo TTS cases, reported with a complete denominator, confirms 46 masked false negatives, 9 exposed TTS errors, and 55 cases with no Raw TTS error. A span-isolation diagnostic re-exposes 18/46 previously masked errors. A Raw-only CosyVoice audit on the same targeted pool confirms 51 masked cases. Across the 97 TTS-specific audio files labeled confirmed masked across the two audits, Qwen3-ASR surface-recovers 40 cases, whereas Paraformer does so in only 2. The results suggest that ASR-roundtrip is useful for screening but insufficient as standalone ground truth for Chinese news reading-risk evaluation.
Yuqian Zhang, Yao Shi, Kexin Huang +7cs.SD cs.AI cs.CL
Zero-shot text-to-speech (TTS) now supports interactive assistants, personalized media, and accessibility tools. All TTS systems require faithful linguistic rendering, consistent speaker identity, and low-latency response. Yet compact streaming systems must preserve sufficient acoustic detail in a predictable low-rate latent sequence, while iterative diffusion sampling and classifier-free guidance multiply inference cost at every autoregressive step. To strike a balance between high-fidelity synthesis and low-latency inference, we present CuteTTS, a compact continuous-autoregressive TTS system. It combines semantically aligned causal VAE latents with patch-level autoregression, explicit speaker conditioning, and a bidirectional flow-matching head. We further introduce guidance-step distillation, which absorbs classifier-free guidance and multiple solver steps into a single interval-conditioned student. Evaluations on LibriSpeech and Seed-TTS-Eval demonstrate competitive intelligibility and speaker similarity in zero-shot voice cloning, while distillation lowers first-audio latency by 23.3% and real-time factor by 40.8% relative to the base model with comparable objective and subjective quality. These results provide a practical path toward continuous-autoregressive TTS that reconciles high-fidelity generation with the latency demands of real-time interaction.
Karim Benharrak, Oriol Nieto, Bryan Wang +2cs.HC cs.AI cs.MM
Audio dramas weave dialogue, sound effects, and music into immersive stories. Creators often adapt books into audio dramas, but this process remains labor-intensive, requiring them to interpret source material, author scripts, generate audio assets, and assemble them on a timeline. Because story elements like characters and scenes manifest across many interdependent assets, a single change can ripple into manual updates across the entire project. We present Dramarrator, an audio drama authoring tool built around object-based audio editing, where these story elements are represented as editable objects. Dramarrator extracts these objects from a book, generates linked audio assets (speech, sound effects, and music), and composes a multi-track audio drama. Edits to any object (e.g., a character's voice) automatically propagate to all dependent assets. In a user study with professionals (N=8), Dramarrator significantly lowered task load when creating audio dramas. A listener study (N=300) shows that creator-refined output from Dramarrator approaches the quality of productions made with existing professional tools, and an exploratory study (N=3) suggests object-based editing lowers entry barriers and generalizes beyond audio dramas.
Reinforcement learning for flow-matching text-to-speech is complicated by deterministic ODE sampling: trajectory-level policy-gradient methods typically convert the ODE into an SDE and track per-step likelihood ratios, introducing stochastic perturbations and substantial overhead. We propose GROW, a group-relative advantage-weighted on-policy RL method that acts directly on the standard flow-matching objective. For each prompt, GROW samples a group of on-policy utterances, separately standardizes intelligibility and speaker-similarity rewards within the group, and combines them to reweight flow-matching regression. A Wasserstein-2 velocity penalty anchors the updated model to a frozen pretrained reference. A group-mean reward baseline is introduced to convert reward weighting into advantage weighting. For strong pretrained TTS models with concentrated rewards, positive exponential weighting is dominated by reward-agnostic self-imitation, whereas a zero-mean signed advantage preserves effective within-group credit assignment. Instantiated on DiTAR and evaluated on LibriSpeech and Seed-TTS EN/ZH, GROW reduces average WER from 2.016 to 1.558 and raises speaker similarity from 0.676 to 0.715 while keeping UTMOS. With 10-NFE training rollouts and 32-NFE evaluation, GROW retains comparable performance while training 2.9x faster than 32-NFE DiTAR-GRPO. We will open-source complete GROW codes, faithful DiTAR reproduction, and all model checkpoints.
Ali Jafar, Amal Sarmad, Shifa Yousaf +1cs.CL cs.LG
Recent advances in neural text-to-speech (TTS) systems have substantially improved speech naturalness and intelligibility across many languages. However, comprehensive evaluation methodologies that jointly assess perceptual quality, speaker similarity, and acoustic fidelity across diverse speech domains remain limited, particularly for low-resource and underrepresented languages. This paper presents a reproducible, multi-metric benchmarking framework for systematic evaluation of modern TTS systems through domain-specific analysis. The proposed framework integrates complementary subjective and objective evaluation protocols and is demonstrated through a comprehensive case study on a representative low-resource language spanning four speech domains: Formal, Conversational, Literary/Storytelling, and Emotional. Four state-of-the-art TTS systems -- Indic-Parler-TTS, MMS-TTS, Microsoft Edge TTS, and Google Gemini TTS -- are evaluated using MUSHRA listening tests, ABX discrimination tests, speaker similarity scoring with Resemblyzer, and acoustic analyses based on mel-cepstral distortion (MCD) and F0 RMSE over 960 audio pairs. Results reveal substantial variation in TTS performance across speech domains, with emotional speech consistently presenting the greatest synthesis challenge (mean MCD 12.03 dB; mean F0 RMSE 889 cents), while conversational speech achieves the highest overall acoustic fidelity. Beyond the empirical findings, this work provides a reproducible evaluation framework, publicly releasing evaluation scripts, result tables, and executable Colab notebooks to support standardized benchmarking and future research on TTS evaluation for low-resource languages.
Hankun Wang, Bohan Li, Shi Lian +6cs.SD cs.AI cs.CL eess.AS
Speech editing for content creation requires precise control over both what an edit should do and where it should apply. Free-form natural language provides a flexible interface for expressing edit requests, but its ambiguity may leave the intended operation, parameters, or target region underspecified. We study a precise and explicit interface for speech editing: a transcript-grounded structural edit instruction with XML-style tags explicitly specifies typed operations and localizes them to transcript spans or boundaries. This semantic timeline avoids explicit timestamp alignment and provides an externally inspectable contract for compositional edits. We instantiate the interface in dots$.$tts$.$edit, an editor adapted from the continuous autoregressive dots$.$tts foundation model. Four representative speech-creation controls cover lexical content, affective expression, pitch and speaking-rate delivery, and temporal phrasing through text, emotion, prosody, and pause editing. Task-specific data pipelines construct operation- and scope-controlled pairs while retaining source-derived context outside each target region. We further introduce doteBench, a bilingual evaluation suite that measures precise instruction following, local preservation, and audio quality across the four controls and their composition. Experiments show leading overall instruction following and local preservation across its five editing categories, while audio quality remains comparable to existing open-source systems. Across three Seed-TTS-Eval shards, the model shows negligible differences from the base model in zero-shot TTS recognition error rate and speaker similarity.
Chenlin Liu, Minghui Fang, Zhonghao Bi +3eess.AS cs.LG eess.SP
Language model-based text-to-speech (LM-based TTS) remains vulnerable to speech hallucinations that deviate from the target text. Existing mitigation mainly relies on architectural changes or additional training, while decoding-time control remains underexplored. We present a conditional information view that distinguishes text-derived alignment information from experience information supplied by acoustic context and learned speech regularities. We hypothesize that an important class of hallucinations begins when alignment support is insufficiently reflected in the selected token at a vulnerable transition. Using predictions from the same speech LM with and without text conditions, we propose Experience-Calibrated Contrastive Decoding (ECCD), a training-free method that strengthens alignment support while preserving useful experience information. ECCD preserves the original expert distribution, applies only positive alignment enhancement, and calibrates its strength using set-level experience compatibility. Across four models, ECCD reduces WER/CER by up to 55.6% in all SeedTTS-Eval settings and 24 of 25 multilingual CV3-Eval settings. A listening test yields a CMOS gain of $+0.644$ while retaining strong speaker similarity. Further analysis shows that alignment influence and decision-level gain vary within linguistic units and are lower at first-error boundaries than at matched correct boundaries. Overall, these extensive experiments and analyses identify conditional information control as a promising decoding-time direction for mitigating speech hallucination.
Siri Expressive Voices synthesize rich, configurable speech in real time and entirely on device, powered by AFM 3 Core Advanced, Apple's most powerful on-device foundation model. This work presents the memory-efficient audio synthesis architecture behind that capability: a detokenizer that converts the semantic audio tokens emitted by the foundation model into high-fidelity audio within the tight compute and memory budget of the Apple Matrix Coprocessor (AMX). We convert semantic audio tokens to a residual vector quantization (RVQ) representation with a three-component design, a streaming encoder, a temporal decoder, and a depth decoder, that systematically decouples temporal and depth processing. A single reusable depth decoder with Diffusion Transformer (DiT)-style stage conditioning generates all RVQ levels autoregressively, replacing the dedicated per-level decoders of prior multi-decoder architectures, while causal sliding window attention with fixed-window key-value caching yields constant memory complexity independent of sequence length. Deployed on the AMX, the detokenizer sustains roughly 10 ms per generation step, about 16x faster than real time, with a peak runtime memory of only 21 MB and 329 MB of on-device assets, enabling continuous streaming synthesis of 20-320 seconds of audio. This constant, small footprint replaces the linear and quadratic memory scaling of conventional transformer- and GAN-based approaches. Ablation studies validate the key architectural components, and audio quality assessment confirms that the architecture maintains synthesis fidelity while achieving efficiency gains over existing methods. Operating at a 1-billion-parameter activation size within AFM 3 Core Advanced, it improves Mean Opinion Score by +0.28 overall (4.15 vs. 3.87) and by +0.42 on conversational speech (4.24 vs. 3.82) over the prior on-device text-to-speech system.
Autoregressive text-to-speech models achieve strong naturalness but suffer from slow inference due to sequential token generation, limiting their deployment in production applications that require low latency. IndexTTS-2 is a state-of-the-art autoregressive TTS model consisting of a GPT, a flow-matching Diffusion Transformer, and a vocoder. Despite its high synthesis quality, its inference speed barely reaches real-time without streaming or batching support. We present Faster IndexTTS-2, which accelerates all neural network components of IndexTTS-2 for production deployment on GPUs using NVIDIA TensorRT and TensorRT-LLM. Faster IndexTTS-2 also enables streaming synthesis for latency-sensitive interactive applications, and batched inference across all components to maximize GPU utilization. Experiments on the Seed-TTS benchmark for both English and Chinese demonstrate up to 5.0$\times$ speedup on the autoregressive GPT and 3.6$\times$ end-to-end, with minimal degradation in word error rate, speaker similarity, and naturalness. Our methodology provides a practical reference for efficiently accelerating similar autoregressive speech models on GPUs.
We present a practical recipe for building a compact Hindi text-to-speech (TTS) model by distilling a large flow-matching teacher (IndicF5, 337M-parameter DiT) under a severe data budget (~17.6 hours). Training a small model from scratch on this much data fails outright. Instead we warm-start the student from the teacher by pruning depth only: keeping the teacher's width, text dimension, attention heads, and mel/text I/O fixed so all non-block tensors copy one-to-one, and retaining an evenly-spaced subset of transformer blocks. We first measure how much depth the teacher tolerates (it remains near-functional at -27% blocks but collapses past -50%), then descend gradually (22 -> 16 -> 12 -> 8 -> 6 blocks), re-fine-tuning after each prune, with each step gated by an objective ASR word-error-rate (WER) check. The resulting students reach WER 0.00 on unseen sentences at 249M and 190M parameters, and remain robust down to 131M; at 102M we observe a clear capacity cliff that we attribute to the data budget rather than the recipe. We also document two train/inference feature- and library-parity failures (mel filterbank and rotary-embedding library versions) that silently degrade audio, and a version-independent fix. The method yields a high-quality Hindi voice that runs in real time on a 6 GB laptop GPU. An independent 50-sentence FLEURS benchmark compares the released 190M student against its teacher and MMS-TTS-hin.
People with low vision often face challenges in performing everyday tasks that require interpreting visual information. We present \textbf{VisionAssist}, an open-source mobile application designed to improve independence by providing AI-powered visual assistance through a smartphone. The application integrates three complementary functionalities within a single interface. First, it enables users to locate specific objects by analyzing the live camera feed. Second, it generates spoken descriptions of captured images, allowing users to identify visual content such as food labels, documents, and everyday objects. Third, it integrates with the smartphone's contacts and calendar to facilitate emergency calls and provide voice-based reminders. The application supports hands-free interaction through voice commands and delivers all feedback using text-to-speech synthesis, making it fully accessible to users with visual impairments. By combining multiple assistive services into a unified platform and releasing the project as open-source software, the proposed solution aims to encourage community contributions and accelerate the development of accessible technologies. The source code is publicly available at: https://github.com/AOzlemC/LowVisionProject.git
Kola Tubosun, Adedayo Oluokun, Hafiz Adewuyi +1cs.SD cs.CL eess.AS
We present TTSYoruba, a rule-based concatenative diphone speech synthesizer for Yoruba, deployed at online as part of the YorubaName.com open dictionary of Yoruba personal names. The system takes tone-marked Yoruba text as input and produces audio output by applying a hand-crafted phonological rule system to a recorded inventory of 651 diphone units spanning five tonal variants of every consonant-vowel combination in the language. We describe the phonological architecture of the system in detail, including our complete tonal file-selection logic, our treatment of the three-way nasal disambiguation problem (oral /n/, nasalized vowel, and syllabic nasal), and the derivation of contextual rising and falling tones from level-tone input. We also present, as an orthographic contribution, the adoption of the caron and circumflex, which are symbols with prior standing in Yoruba phonological transcription, as standard single-vowel contour tone markers, integrated into the TTS normalization pipeline and the WriteYoruba keyboard input tool. The system's performance was evaluated through a listener study (N=50), with detailed results on Mean Opinion Scores (MOS) presented in Section 6. Keywords: Yoruba, text-to-speech, low-resource languages, diphone synthesis, contour tones, African language NLP, rule-based synthesis
Modern LLM-driven text-to-speech (TTS) and voice conversion (VC) systems produce synthetic speech that differs from the generators represented in many legacy spoofing benchmarks. This mismatch creates a temporal generalization gap that can overestimate detector robustness under real-world post-processing conditions. We bridge this gap by introducing VoxENES 2026, a bilingual (English and Spanish) benchmark of 53,628 audio samples generated using 10 contemporary speech synthesis methods and evaluated under 10 standardized post-processing conditions. Using VoxENES 2026, we benchmark eight pretrained detectors without fine-tuning and observe substantial performance degradation: the best model achieves 28.98\% EER overall, while most perform near or below random chance across modern generators and perturbations. Our results highlight the reliance on brittle artifacts in current detectors and establish VoxENES 2026 as a practical testbed for developing robust audio spoofing countermeasures.
Ahmet Erdem Pamuk, Ömer Yentür, Ahmet Tunga Bayrak +2cs.CL
We introduce Freya-TTS, a compact, tokenizer-free, Turkish-first text-to-speech model designed for highly reliable and efficient conversational synthesis. Freya-TTS is a 183.2M-parameter non-autoregressive conditional flow-matching Diffusion Transformer (DiT) that operates in the continuous latent space of the frozen AudioVAE2 (16 kHz encode, 48 kHz decode), allowing the model to focus its capacity on text-to-latent mapping while inheriting high-quality 48 kHz reconstruction. We advance the framework along three key dimensions: (1) rule-free end-to-end modeling from a 92-symbol Turkish character vocabulary without a phonemizer, grapheme-to-phoneme frontend, or discrete speech tokenizer, with digit strings expanded to their spoken form at the text frontend; (2) non-autoregressive parallel denoising, which predicts the entire latent sequence simultaneously over a predicted duration; and (3) a production-oriented two-stage post-training recipe consisting of single-speaker voice locking and short-utterance coverage, improving speaker consistency and robustness on short inputs. On the Freya-TR-Eval benchmark, Freya-TTS achieves a band-matched word error rate (WER) of 8.0% and character error rate (CER) of 3.0%, lower error than both larger open systems in its field, XTTS-v2 and F5-TTS, at 40-55% of their parameter count, together with the highest naturalness (MOS) among the compact systems. The model achieves a real-time factor of 0.11 on a consumer GPU (RTX 4090; ~0.14 mean on an H100) and synthesizes in real time on a laptop CPU, making it well suited for resource-constrained edge deployment. We release the model weights, training and inference code, and evaluation benchmark under the Apache-2.0 license.
Representation alignment (REPA) has been investigated to accelerate diffusion training, but we observe that regularizing intermediate representations in diffusion Transformers (DiT) may implicitly entangle latents and limit generative capacity. To address this issue, we propose ReGen, a hierarchical multi-prompt representation generation framework that jointly estimates multiple vector fields for both representations and data within a single diffusion model. We further introduce generalized flow matching (GFM) to improve the generalization of conditional flow matching (CFM). We validate ReGen on single-stage waveform diffusion models including neural audio codec and Wave-VAE. ReGen significantly improves waveform generation quality from highly compressed latent representations at 12.5 Hz. We also present ReGenVoice, a latent diffusion model (LDM)-based text-to-speech model that achieves strong speech intelligibility (WER) and speaker similarity (SIM) with a small dataset. Moreover, operating the LDM at 6.25 Hz with rich semantic and acoustic latent representation enables efficient training and sampling, requiring only 1 day of training on 4 GPUs and fast inference with an RTF of 0.08. Audio samples are available at https://regenvoice.github.io/demo/.
Best-of-$N$ (BoN) inference improves content consistency in zero-shot text-to-speech by selecting from $N$ candidates with an automatic speech recognition (ASR) verifier. We identify an underexplored evaluation confound: a verifier's apparent quality depends strongly on which ASR family judges it. On LibriSpeech-PC test-clean~\citep{librispeechpc} with F5-TTS~\citep{f5tts}, verifier rankings reverse across Whisper, wav2vec~2.0, and HuBERT evaluators, and same-family verifier-evaluator pairs recover 2-3$\times$ more oracle headroom than cross-family pairs despite near-identical representations (linear CKA $0.978$) -- a pattern consistent with identity- or lineage-level coupling rather than representational overlap. We propose two \textbf{cross-family rank ensembles} (rank-averaging and conjunctive max-rank) that attain the lowest mean WER across three independent evaluators -- $1.61\%$ at $N{=}10$ ($-12\%$ relative to F5-TTS) -- with no measurable degradation under automatic SIM-o/UTMOS metrics; the best single verifier drives WER from $2.06\%$ to $1.72\%$ ($-16.5\%$) under the official F5-TTS evaluator. We recommend cross-evaluator triangulation as default reporting practice.