PilotTTS: A Disciplined Modular Recipe for Competitive Speech Synthesis

• URL: http://arxiv.org/abs/2605.27258v2
• Date: Wed, 27 May 2026 06:28:23 GMT
• Title: PilotTTS: A Disciplined Modular Recipe for Competitive Speech Synthesis
• Abstract summary: We present PilotTTS, a lightweight autoregressive text-to-speech system.<n>PilotTTS achieves competitive performance through minimalist architecture and rigorous data engineering.<n>PilotTTS is trained on only 200K hours of data processed entirely with open-source tools.
• Score: 16.983092337406138
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Building state-of-the-art text-to-speech (TTS) systems typically demands millions of hours of proprietary data and complex multi-stage architectures, creating substantial barriers for resource-constrained research teams. In this report, we present PilotTTS, a lightweight autoregressive TTS system that achieves competitive performance through minimalist architecture and rigorous data engineering. PilotTTS is trained on only 200K hours of data processed entirely with open-source tools. Specifically, our contributions are: (1) a reproducible multi-stage data processing pipeline covering quality assessment, label annotation, and filtering, and (2) a compact model architecture that employs Q-Former-based conditioning to decouple speaker identity from speaking style via cross-sample paired training. Within a unified framework, PilotTTS supports zero-shot voice cloning, emotion synthesis (11 categories), paralinguistic synthesis (4 categories), and Chinese dialect synthesis (14 dialects). On the Seed-TTS Eval benchmark, PilotTTS achieves the lowest WER of 1.50% on test-en, a CER of 0.87% on test-zh, and the highest speaker similarity on both test sets (0.862 and 0.815), outperforming systems trained on significantly larger datasets. We release the complete data pipeline recipe, pretrained weights, and code at https://github.com/AMAPVOICE/PilotTTS.

Related papers

• KIT's Low-resource Speech Translation Systems for IWSLT2025: System Enhancement with Synthetic Data and Model Regularization [64.1520245849231]
  This paper presents KIT's submissions to the IWSLT 2025 low-resource track.<n>We develop both cascaded systems, and end-to-end (E2E) Speech Translation systems.<n>Building upon pre-trained models, we fine-tune our systems with different strategies to utilize resources efficiently.
  arXiv  Detail & Related papers  (2025-05-26T08:38:02Z)
• Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens [31.575335190916995]
  We introduce Spark-TTS, a novel system powered by BiCodec, a single-stream speech that decomposes speech into two complementary token types.<n>To facilitate research in controllable TTS, we introduce VoxBox, a meticulously curated 100,000-hour dataset with comprehensive attribute annotations.
  arXiv  Detail & Related papers  (2025-03-03T16:23:10Z)
• Fast Streaming Transducer ASR Prototyping via Knowledge Distillation with Whisper [3.717584661565119]
  We demonstrate that streaming Transformer-Transducer (TT) models can be trained from scratch without supervised data. This allows training a robust ASR model just in one stage and does not require large data and computational budget. We validate the proposed framework on 6 languages from CommonVoice and propose multiple filters to filter out hallucinated PLs.
  arXiv  Detail & Related papers  (2024-09-20T13:38:59Z)
• SpoofCeleb: Speech Deepfake Detection and SASV In The Wild [76.71096751337888]
  SpoofCeleb is a dataset designed for Speech Deepfake Detection (SDD) and Spoofing-robust Automatic Speaker Verification (SASV)<n>SpoofCeleb comprises over 2.5 million utterances from 1,251 unique speakers, collected under natural, real-world conditions.
  arXiv  Detail & Related papers  (2024-09-18T23:17:02Z)
• Improving Text Embeddings with Large Language Models [59.930513259982725]
  We introduce a novel and simple method for obtaining high-quality text embeddings using only synthetic data and less than 1k training steps. We leverage proprietary LLMs to generate diverse synthetic data for hundreds of thousands of text embedding tasks across 93 languages. Experiments demonstrate that our method achieves strong performance on highly competitive text embedding benchmarks without using any labeled data.
  arXiv  Detail & Related papers  (2023-12-31T02:13:18Z)
• Matcha-TTS: A fast TTS architecture with conditional flow matching [13.973500393046235]
  We introduce Matcha-TTS, a new encoder-decoder architecture for speedy TTS acoustic modelling. It is trained using optimal-transport conditional flow matching (OT-CFM) This yields an ODE-based decoder capable of high output quality in fewer synthesis steps than models trained using score matching.
  arXiv  Detail & Related papers  (2023-09-06T17:59:57Z)
• Strategies for improving low resource speech to text translation relying on pre-trained ASR models [59.90106959717875]
  This paper presents techniques and findings for improving the performance of low-resource speech to text translation (ST) We conducted experiments on both simulated and real-low resource setups, on language pairs English - Portuguese, and Tamasheq - French respectively.
  arXiv  Detail & Related papers  (2023-05-31T21:58:07Z)
• MnTTS: An Open-Source Mongolian Text-to-Speech Synthesis Dataset and Accompanied Baseline [16.95694149810552]
  This paper introduces a high-quality open-source text-to-speech dataset for Mongolian, a low-resource language spoken by over 10 million people worldwide. The dataset, named MnTTS, consists of about 8 hours of transcribed audio recordings spoken by a 22-year-old professional female Mongolian announcer. It is the first publicly available dataset developed to promote Mongolian TTS applications in both academia and industry.
  arXiv  Detail & Related papers  (2022-09-22T08:24:43Z)
• ESPnet2-TTS: Extending the Edge of TTS Research [62.92178873052468]
  ESPnet2-TTS is an end-to-end text-to-speech (E2E-TTS) toolkit. New features include: on-the-fly flexible pre-processing, joint training with neural vocoders, and state-of-the-art TTS models with extensions like full-band E2E text-to-waveform modeling.
  arXiv  Detail & Related papers  (2021-10-15T03:27:45Z)
• You Do Not Need More Data: Improving End-To-End Speech Recognition by Text-To-Speech Data Augmentation [59.31769998728787]
  We build our TTS system on an ASR training database and then extend the data with synthesized speech to train a recognition model. Our system establishes a competitive result for end-to-end ASR trained on LibriSpeech train-clean-100 set with WER 4.3% for test-clean and 13.5% for test-other.
  arXiv  Detail & Related papers  (2020-05-14T17:24:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.