Pith. sign in

REVIEW 11 cited by

E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.18009 v2 pith:6TP5GV3F submitted 2024-06-26 eess.AS cs.SD

Sefik Emre Eskimez , Xiaofei Wang , Manthan Thakker , Canrun Li , Chung-Hsien Tsai , Zhen Xiao , Hemin Yang , Zirun Zhu
show 5 more authors
Min Tang Xu Tan Yanqing Liu Sheng Zhao Naoyuki Kanda
This is my paper
classification eess.AScs.SD
keywords zero-shoteasyembarrassinglyfullyinputnon-autoregressiveprevioussimplicity
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper introduces Embarrassingly Easy Text-to-Speech (E2 TTS), a fully non-autoregressive zero-shot text-to-speech system that offers human-level naturalness and state-of-the-art speaker similarity and intelligibility. In the E2 TTS framework, the text input is converted into a character sequence with filler tokens. The flow-matching-based mel spectrogram generator is then trained based on the audio infilling task. Unlike many previous works, it does not require additional components (e.g., duration model, grapheme-to-phoneme) or complex techniques (e.g., monotonic alignment search). Despite its simplicity, E2 TTS achieves state-of-the-art zero-shot TTS capabilities that are comparable to or surpass previous works, including Voicebox and NaturalSpeech 3. The simplicity of E2 TTS also allows for flexibility in the input representation. We propose several variants of E2 TTS to improve usability during inference. See https://aka.ms/e2tts/ for demo samples.

Discussion (0). Sign in to comment.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. StellarTTS: Sparse Temporal Embedding for Low-Latency and Robust Speech Synthesis

    cs.SD 2026-07 conditional novelty 6.0 of 10

    A mobile-oriented 83M-parameter masked transformer with sparse phone-anchored temporal embeddings achieves RTF 0.08 and lower WER than MaskGCT/F5-TTS on Seed-TTS test sets.

  2. Best-of-$N$ TTS Evaluation is Confounded by ASR Family Alignment

    cs.CL 2026-07 conditional novelty 6.0 of 10

    BoN TTS verifier rankings reverse across ASR families; same-family pairs recover 2–3× more oracle headroom, and cross-family rank ensembles give the most robust WER gains.

  3. Next Tokens Denoising for Speech Synthesis

    cs.SD 2025-07 conditional novelty 6.0 of 10

    Dragon-FM generates speech autoregressively over two-second chunks while using flow matching inside each chunk, achieving fast synthesis at 12.5 discrete audio tokens per second.

  4. DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis

    eess.AS 2025-07 conditional novelty 6.0 of 10

    Reinforcement learning on duration prediction improves intelligibility and speaker similarity in a 4-step distilled text-to-speech model, and teacher-guided sampling recovers prosodic diversity.

  5. Transcript-Prompted Whisper with Dictionary-Enhanced Decoding for Japanese Speech Annotation

    cs.CL 2025-06 conditional novelty 6.0 of 10

    A transcript-prompted Whisper model with dictionary-based decoding automatically produces phonemic and prosodic annotations for Japanese audio-transcript pairs, improving Japanese TTS naturalness.

  6. RASMALAI: Resources for Adaptive Speech Modeling in Indian Languages with Accents and Intonations

    cs.CL 2025-05 conditional novelty 6.0 of 10

    A new 13,000-hour dataset with 24 million LLM-generated text descriptions enables the first open-source text-driven TTS for 24 Indian languages, with reported high speaker, emotion, and cross-lingual control.

  7. Qwen-Audio-3.0-TTS: Freely Controllable and Highly Robust Speech Synthesis with Multi-Stage Training Paradigm

    eess.AS 2026-07 conditional novelty 5.0 of 10

    Qwen-Audio-3.0-TTS claims state-of-the-art controllable multilingual text-to-speech across 16 languages and 20 Chinese dialects, using a 12.5 Hz tokenizer and multi-stage RL.

  8. Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey

    cs.CV 2026-04 unverdicted novelty 5.0 of 10

    The paper offers the first focused review of MLLM-based video translation organized by a three-role taxonomy of Semantic Reasoner, Expressive Performer, and Visual Synthesizer, plus open challenges.

  9. CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis

    eess.AS 2025-08 conditional novelty 5.0 of 10

    CLEAR is a zero-shot TTS model that autoregressively predicts compact continuous audio latents with a per-token rectified flow head, reaching 1.88% WER on LibriSpeech Subset-B with an RTF of 0.29 and a 96 ms streaming delay.

  10. DETECT-3B-Omni is Agnostic of Content and Demographics

    cs.SD 2026-07 conditional novelty 4.0 of 10

    Equivalence tests on 10,240 samples find DETECT-3B-Omni accuracy differs by ≤2pp across content type and speaker demographics at 99% confidence.

  11. EZ-VC: Easy Zero-shot Any-to-Any Voice Conversion

    cs.SD 2025-05 reject novelty 4.0 of 10

    EZ-VC combines discrete units from a multilingual self-supervised encoder (Xeus) with an F5-TTS flow-matching decoder to achieve zero-shot any-to-any voice conversion, without text labels or multiple disentangling encoders.

Pith tools